© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13337
    Prev
    Next
    INDEX
    Explanations

    formal language relating to scientific or technical descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    formal academic prose, especially passive-voice methodological statements and logical connectives alongside technical symbols and numerals typical of equations and measurements.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    Looking at the activations, this neuron responds most strongly to words like "we", "can", "be", "as", "it", "1", "After", "will", "there", "prototype", "estimated", "approximately", "performed", "the", "based on

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ब्रेकडाउन
    -0.54
    xase
    -0.50
    saraba
    -0.46
     الحره
    -0.45
    Skocz
    -0.41
    protoimpl
    -0.41
    RegistryLite
    -0.40
     Avez
    -0.40
    MemoryWarning
    -0.40
     beginnetje
    -0.39
    POSITIVE LOGITS
     autorytatywna
    0.50
     AssemblyTitle
    0.45
     Camer
    0.44
    ssp
    0.44
     Cosa
    0.43
     teka
    0.42
    alek
    0.42
     AssemblyCulture
    0.42
    Camer
    0.41
     Tala
    0.41
    Activations Density 1.536%

    No Known Activations