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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 16302
    Prev
    Next
    INDEX
    Explanations

    instances of public disclosures and the implications of information release

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     surla
    -0.47
    chism
    -0.40
    phosa
    -0.40
    reactstrap
    -0.36
     hObject
    -0.35
    literals
    -0.35
    KommentareTeilen
    -0.35
     recensement
    -0.33
    batore
    -0.33
    ynthia
    -0.33
    POSITIVE LOGITS
     public
    3.77
     Public
    2.97
    Public
    2.95
    public
    2.92
     PUBLIC
    2.89
     pública
    2.70
     publicly
    2.69
     público
    2.66
    PUBLIC
    2.53
     publique
    2.52
    Activations Density 0.477%

    No Known Activations