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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 120307
    Prev
    Next
    INDEX
    Explanations

    positive sentiment and expressions of hopefulness or improvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -0.58
     henvisninger
    -0.41
    ‌است
    -0.37
    InjectAttribute
    -0.37
     epä
    -0.37
     Protobuf
    -0.37
    windowFixed
    -0.35
    最快更新
    -0.33
    esModule
    -0.33
     réussir
    -0.33
    POSITIVE LOGITS
     &___
    0.49
    ronpa
    0.45
    NewReader
    0.44
    terer
    0.43
    ChrTalk
    0.43
    hör
    0.42
    ActivityResult
    0.41
    blik
    0.41
    Jereo
    0.41
    voye
    0.41
    Activations Density 0.103%

    No Known Activations