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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 5107
    Prev
    Next
    INDEX
    Explanations

    phrases indicating aspirations and future goals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    creen
    -0.50
    wesen
    -0.49
    gent
    -0.46
    rowad
    -0.45
    idity
    -0.45
    gens
    -0.44
     facilitating
    -0.43
     screening
    -0.43
    ğinde
    -0.42
    fillType
    -0.42
    POSITIVE LOGITS
    脚注の使い方
    0.87
    AndEndTag
    0.78
     AssemblyCulture
    0.70
    meanor
    0.63
    的目标
    0.62
    ^(@)
    0.59
     estekak
    0.59
     EconPapers
    0.59
     goals
    0.58
    IntoConstraints
    0.58
    Activations Density 0.149%

    No Known Activations