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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 6-GEMMASCOPE-RES-16K
    6. 5234
    Prev
    Next
    INDEX
    Explanations

    HTML tags used for formatting emphasis in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Билгалдахарш
    -0.81
     ویکی‌پدیا
    -0.77
    IntoConstraints
    -0.75
    WithMany
    -0.74
    endphp
    -0.73
    SharedCtor
    -0.72
     صوتيه
    -0.71
    Демографія
    -0.71
    슷
    -0.69
    expandindo
    -0.69
    POSITIVE LOGITS
    <strong>
    0.90
    <b>
    0.71
    <em>
    0.62
    textbf
    0.55
    mathbf
    0.48
     masing
    0.45
    bold
    0.45
    #
    0.44
    Afrika
    0.44
     OGSÅ
    0.44
    Activations Density 0.025%

    No Known Activations