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. 10-GEMMASCOPE-RES-16K
    6. 11777
    Prev
    Next
    INDEX
    Explanations

    statistics and discussions related to poverty rates and socioeconomic conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ScopeManager
    -0.70
    OGND
    -0.57
    EndInit
    -0.54
    Autoritní
    -0.53
    tagHelperRunner
    -0.52
    delwed
    -0.51
    ViewImports
    -0.51
     Chwiliwch
    -0.50
    contentLoaded
    -0.47
     själv
    -0.47
    POSITIVE LOGITS
     localVar
    0.60
    ंदीखरीदारी
    0.54
     vực
    0.53
    oudoune
    0.52
    pared
    0.51
     ElevatedButton
    0.51
    />";
    0.51
    endphp
    0.51
    PARED
    0.50
    펴
    0.50
    Activations Density 0.535%

    No Known Activations