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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 3744
    Prev
    Next
    INDEX
    Explanations

    descriptions of car features and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Preceding car models/features

    np_acts-logits-general · gemini-2.0-flash

    vehicle exterior design

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     NSCoder
    -0.43
     pending
    -0.39
    uchi
    -0.38
     незавершена
    -0.36
    riel
    -0.36
    tained
    -0.36
     mere
    -0.36
     Defend
    -0.34
    adapt
    -0.33
    letti
    -0.33
    POSITIVE LOGITS
    featureID
    0.56
     ब्रेकडाउन
    0.56
    WithIOException
    0.54
    parency
    0.51
    Identyfik
    0.51
    zzleHttp
    0.50
    protoc
    0.49
    tagext
    0.48
    EndContext
    0.47
    windowFixed
    0.46
    Activations Density 0.105%

    No Known Activations