© 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. 3-GEMMASCOPE-RES-16K
    6. 7906
    Prev
    Next
    INDEX
    Explanations

    tokens or symbols indicating coding sequences or genetic information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LookAnd
    -0.50
    astify
    -0.49
    matchCondition
    -0.47
    jspx
    -0.46
    ţion
    -0.46
    SuccessListener
    -0.45
     oprot
    -0.45
     mắn
    -0.45
    lihood
    -0.44
     pinulongan
    -0.44
    POSITIVE LOGITS
    Hentet
    0.51
     UITableView
    0.36
    Atra
    0.35
     tut
    0.35
     ого
    0.34
     gevo
    0.34
     CanadaChoose
    0.34
     undated
    0.33
     navideñas
    0.33
    pdf
    0.33
    Activations Density 0.439%

    No Known Activations