© 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. 28-GEMMASCOPE-RES-16K
    11. 5004
    Prev
    Next
    INDEX
    Explanations

    technical terms related to frameworks and programming conventions

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

    following "the," "a," or "unlike."

    np_acts-logits-general · gemini-2.0-flash

    conventional or unlike

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anskje
    -0.54
     Biôgrafia
    -0.49
    ="@+
    -0.47
    TypedDataSet
    -0.47
    ThroughAttribute
    -0.46
    brigens
    -0.46
    Rohy
    -0.44
    czegó
    -0.44
    Географиясе
    -0.44
     utafitiHapana
    -0.44
    POSITIVE LOGITS
     traditional
    2.56
     conventional
    2.41
    traditional
    2.23
    conventional
    2.11
    Traditional
    2.05
     Traditional
    2.02
     tradicional
    2.02
    Conventional
    1.91
     Conventional
    1.89
     tradizionale
    1.88
    Activations Density 1.603%

    No Known Activations