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. 8-GEMMASCOPE-RES-16K
    6. 2345
    Prev
    Next
    INDEX
    Explanations

    URLs and configuration-related commands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     call
    -0.63
     Mati
    -0.59
    ourable
    -0.57
     Call
    -0.56
    úgó
    -0.56
    ifer
    -0.56
     tempi
    -0.56
    väll
    -0.55
     Karp
    -0.54
     Vend
    -0.53
    POSITIVE LOGITS
     виправивши
    0.94
     Diſ
    0.88
     /\.(
    0.87
     itſelf
    0.84
     Houſe
    0.84
     houſe
    0.84
     ModelExpression
    0.84
     purpoſe
    0.81
     ainfi
    0.78
    SourceChecksum
    0.78
    Activations Density 0.011%

    No Known Activations