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. 4-GEMMASCOPE-RES-16K
    6. 10215
    Prev
    Next
    INDEX
    Explanations

    related to programming constructs and specific functions within a codebase

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PerformLayout
    -0.96
     виправивши
    -0.96
    AccessorTable
    -0.96
    aarrggbb
    -0.74
    OGND
    -0.74
    ніципалі
    -0.73
    Personendaten
    -0.71
     препратки
    -0.71
     TestBed
    -0.70
     StatefulWidget
    -0.70
    POSITIVE LOGITS
    FontStyle
    0.56
     consecuencias
    0.51
    schedulers
    0.49
     maternidade
    0.47
    CURLOPT
    0.47
    HttpStatus
    0.45
     nemlig
    0.45
    CascadeType
    0.43
     Ortsteil
    0.43
    apparence
    0.43
    Activations Density 0.770%

    No Known Activations