Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 3435
    Prev
    Next
    INDEX
    Explanations

    strings related to email addresses or similar contact details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.73
     queſto
    -0.71
    EDEFAULT
    -0.69
    RenderAtEndOf
    -0.69
     zwiſchen
    -0.68
    ſtre
    -0.67
    CppMethod
    -0.66
    دانشنامهٔ
    -0.63
    EndContext
    -0.62
    <unused0>
    -0.61
    POSITIVE LOGITS
     E
    0.40
     B
    0.38
     D
    0.35
     G
    0.34
     b
    0.34
     W
    0.33
     F
    0.32
     S
    0.32
     g
    0.32
     V
    0.32
    Activations Density 2.775%

    No Known Activations