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. 25-GEMMASCOPE-RES-16K
    6. 8651
    Prev
    Next
    INDEX
    Explanations

    numerical values and quantities in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    čios
    -0.53
    getIcon
    -0.50
    ukų
    -0.49
     Theſe
    -0.47
     --;
    -0.45
     szolg
    -0.45
     ''}
    -0.45
    einem
    -0.45
    bibfield
    -0.45
    onekana
    -0.44
    POSITIVE LOGITS
     HasFactory
    0.74
    principalColumn
    0.73
     AssemblyVersion
    0.70
    sizeCache
    0.67
    UnknownFields
    0.65
     AttributeSet
    0.62
    CloseOperation
    0.61
    aarrggbb
    0.61
    extAlignment
    0.60
     EconPapers
    0.57
    Activations Density 0.160%

    No Known Activations