© 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. 8063
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references to court proceedings

    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
    zerne
    -0.52
     visse
    -0.43
     stream
    -0.42
    ților
    -0.41
    ENTES
    -0.41
    enza
    -0.40
     VIAF
    -0.39
     byd
    -0.38
    ensure
    -0.38
     faciliter
    -0.37
    POSITIVE LOGITS
    WEBPACK
    0.82
    ConstraintMaker
    0.81
    AlterField
    0.80
    Jeografia
    0.80
    addCriterion
    0.79
     ModelExpression
    0.78
    ReusableCell
    0.77
    DockStyle
    0.73
     viewDidLoad
    0.72
    BagLayout
    0.72
    Activations Density 2.283%

    No Known Activations