© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 15453
    Prev
    Next
    INDEX
    Explanations

    instances of being informed or notified about various situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     poveznice
    -0.64
     rada
    -0.54
     intervened
    -0.52
    ibrill
    -0.52
    bergh
    -0.51
    zium
    -0.50
    ształ
    -0.50
     ayude
    -0.50
    anguages
    -0.50
    ękuję
    -0.49
    POSITIVE LOGITS
    ScopeManager
    0.73
    migrationBuilder
    0.72
    queryInterface
    0.67
     ++)
    0.63
    addCriterion
    0.61
    MLLoader
    0.60
    jstor
    0.57
    новништво
    0.56
    textAppearance
    0.56
    UserScript
    0.55
    Activations Density 0.268%

    No Known Activations