© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 1924
    Prev
    Next
    INDEX
    Explanations

    technical and scientific terminology related to properties, measurements, and analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MaterialApp
    -0.46
     ExecuteAsync
    -0.43
     AssemblyCulture
    -0.43
    ikä
    -0.41
     relativistic
    -0.41
    Diweddarwch
    -0.41
    IsMutable
    -0.40
     nakalista
    -0.40
    ragalactic
    -0.40
    Zubereitung
    -0.40
    POSITIVE LOGITS
    省市镇
    0.49
     who
    0.48
    Panamoan
    0.46
     ujednoznacz
    0.45
     tewas
    0.43
     whose
    0.43
     ditangkap
    0.43
     defaultstate
    0.42
    gilan
    0.42
     noqa
    0.41
    Activations Density 1.180%

    No Known Activations