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. 31-GEMMASCOPE-RES-16K
    6. 15870
    Prev
    Next
    INDEX
    Explanations

    the presence of parentheses, indicating sourcing or quoting of information in the text

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

    Text within parentheses

    np_acts-logits-general · gemini-2.0-flash

    news agency openers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    globalData
    -0.36
    GEBURTSDATUM
    -0.33
     Elapsed
    -0.32
    UnusedPrivate
    -0.32
    routeProvider
    -0.32
    braith
    -0.31
    нрави
    -0.31
    IBOutlet
    -0.30
     eyes
    -0.30
    WarningLevel
    -0.30
    POSITIVE LOGITS
     nakalista
    0.62
    pushFollow
    0.60
    
    0.49
     pleaſure
    0.48
    CppMethod
    0.48
    mappedBy
    0.48
    Erreferentziak
    0.47
    Tikang
    0.46
    tlement
    0.46
    __((
    0.46
    Activations Density 0.096%

    No Known Activations