© 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. 0-GEMMASCOPE-RES-16K
    11. 9016
    Prev
    Next
    INDEX
    Explanations

    references to biological processes and experimental methods related to gene silencing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rifle
    -0.54
    Bez
    -0.53
     comb
    -0.53
    \{\\
    -0.52
     perf
    -0.50
     muscle
    -0.50
     squirrel
    -0.49
     scratch
    -0.49
     intro
    -0.49
     ſch
    -0.48
    POSITIVE LOGITS
     virtuales
    0.58
     nahilalakip
    0.57
     Gegenteil
    0.54
     Mehrheit
    0.53
    แห่ง
    0.53
    AccessorTable
    0.53
    occasione
    0.52
    attuale
    0.51
     Erhaltung
    0.51
     Erweiterung
    0.50
    Activations Density 0.217%

    No Known Activations