© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 101032
    Prev
    Next
    INDEX
    Explanations

    specific numeric values and comparisons related to measurements and age

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    above, below, or equal to a value

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     oprot
    -0.50
     للمعارف
    -0.48
    Clik
    -0.45
    FormTagHelper
    -0.43
    UrlResolution
    -0.43
    AnchorTagHelper
    -0.42
    󠁬
    -0.42
    UnusedPrivate
    -0.42
    msgTypes
    -0.42
    Carriera
    -0.42
    POSITIVE LOGITS
     (>
    0.57
     beyond
    0.51
    Beyond
    0.47
     Beyond
    0.47
    Tikang
    0.44
    (>
    0.44
    beyond
    0.43
    jewództ
    0.42
    ніципа
    0.42
    GreaterThan
    0.40
    Activations Density 0.127%

    No Known Activations