© 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. 22-GEMMASCOPE-RES-16K
    11. 14987
    Prev
    Next
    INDEX
    Explanations

    terms related to biological and medical terminology, particularly apoptosis and the regulatory genes involved

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مشين
    -0.80
     snippetHide
    -0.75
     دیکھیے
    -0.75
    WithIOException
    -0.74
    ロウィン
    -0.73
     Normdatei
    -0.72
    IntoConstraints
    -0.71
    SequentialGroup
    -0.71
    Personendaten
    -0.69
     kaarangay
    -0.68
    POSITIVE LOGITS
     Vernunft
    0.34
    per
    0.32
    pro
    0.32
     Verkehr
    0.31
    ,
    0.30
     Ewig
    0.29
    alignSelf
    0.29
    ™
    0.28
     Nachhaltigkeit
    0.28
    bro
    0.28
    Activations Density 2.663%

    No Known Activations