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-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 11984
    Prev
    Next
    INDEX
    Explanations

    dialogue and speech patterns in conversation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.60
    ionales
    -0.56
    aarrggbb
    -0.55
    fillType
    -0.53
    addGap
    -0.53
    <bos>
    -0.49
    $_['
    -0.49
     LUMP
    -0.48
    ]();
    -0.48
     חיצוניים
    -0.48
    POSITIVE LOGITS
    albero
    0.59
     onAnimation
    0.58
    getMenuInflater
    0.56
    Materiál
    0.55
    pushFollow
    0.54
    ់
    0.52
    RetentionPolicy
    0.52
    loem
    0.51
    seamnă
    0.50
    wikidata
    0.50
    Activations Density 0.075%

    No Known Activations