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. 23-GEMMASCOPE-RES-16K
    6. 12394
    Prev
    Next
    INDEX
    Explanations

    code snippets related to error handling and file existence checking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    essoal
    -0.53
    earn
    -0.46
    ViewChild
    -0.46
    GENT
    -0.46
     Eichen
    -0.45
    WireFormatLite
    -0.44
    Vidite
    -0.44
     interrelated
    -0.44
    Perd
    -0.43
     prépar
    -0.43
    POSITIVE LOGITS
     return
    0.81
     skip
    0.79
     considérons
    0.76
     bail
    0.73
     throw
    0.73
     silently
    0.71
     nothing
    0.70
     abort
    0.70
     continue
    0.70
     exit
    0.68
    Activations Density 0.689%

    No Known Activations