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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 9304
    Prev
    Next
    INDEX
    Explanations

    conditional statements or clauses expressed with "if"

    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
    enterOuterAlt
    -0.53
    gsSP
    -0.47
     yyb
    -0.46
    rovnik
    -0.45
    agog
    -0.45
    esas
    -0.45
    dci
    -0.44
    Portail
    -0.43
    opengl
    -0.43
     culminated
    -0.42
    POSITIVE LOGITS
     if
    3.30
     если
    2.88
     якщо
    2.63
     nếu
    2.55
     If
    2.55
     jika
    2.48
     dacă
    2.47
    If
    2.45
     jeśli
    2.45
    if
    2.33
    Activations Density 0.335%

    No Known Activations