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. 19-GEMMASCOPE-RES-16K
    6. 2270
    Prev
    Next
    INDEX
    Explanations

    references to significant events or moments that involve strong emotions or consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awtextra
    -1.03
    migrationBuilder
    -0.91
    addGap
    -0.67
    DispatchToProps
    -0.66
    "`
    -0.65
    المشاركات
    -0.64
    "):
    
    -0.62
    vgl
    -0.61
    סף
    -0.60
     Fig
    -0.60
    POSITIVE LOGITS
    __.
    0.75
    __;
    0.72
    __,
    0.69
     oka
    0.68
    NESS
    0.66
     doigts
    0.65
     sociaux
    0.64
    ер
    0.64
    ness
    0.63
     venons
    0.63
    Activations Density 0.514%

    No Known Activations