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. 11-GEMMASCOPE-RES-16K
    6. 14041
    Prev
    Next
    INDEX
    Explanations

    code structures related to null checks and conditionals in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    비
    -0.44
    bleven
    -0.42
     المعيارى
    -0.42
     to
    -0.42
    anthin
    -0.41
    Point
    -0.41
     point
    -0.41
    般
    -0.40
    devamını
    -0.40
    toList
    -0.38
    POSITIVE LOGITS
    =$?
    0.77
    ScopeManager
    0.77
     >=",
    0.76
    EndGlobalSection
    0.76
    SourceChecksum
    0.71
    </caption>
    0.71
    )__
    0.70
    StoryboardSegue
    0.70
    AutoScaleMode
    0.69
     Савезне
    0.68
    Activations Density 0.194%

    No Known Activations