Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 0-GEMMASCOPE-RES-16K
    6. 8098
    Prev
    Next
    INDEX
    Explanations

    occurrences of the substring 'gu' and method calls represented by the pattern '<>()'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    راط
    -0.53
    ManyToMany
    -0.51
    <h5>
    -0.50
     during
    -0.48
    整
    -0.48
     repeatedly
    -0.46
    发表于
    -0.46
     the
    -0.45
     desig
    -0.45
    </h5>
    -0.44
    POSITIVE LOGITS
    ChildScrollView
    0.88
     Administration
    0.78
    ThroughAttribute
    0.76
     '*':
    0.73
     RoutedEventArgs
    0.73
    iconductor
    0.72
    kracht
    0.72
     RUS
    0.71
     smell
    0.68
     Мексичка
    0.68
    Activations Density 0.091%

    No Known Activations