© 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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 50208
    Prev
    Next
    INDEX
    Explanations

    patterns related to numerical data and statistical analysis

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

    hexadecimal numbers following quantities

    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
    الدراسه
    -0.58
    MessageTagHelper
    -0.45
    .*")]
    -0.36
    thenReturn
    -0.36
     hObject
    -0.35
    WebElementEntity
    -0.34
    Portail
    -0.34
    SpringBootTest
    -0.33
    providedIn
    -0.32
    ptid
    -0.32
    POSITIVE LOGITS
     initComponents
    0.56
    rawDesc
    0.50
    ########.
    0.49
    åringen
    0.49
    AutoScale
    0.48
     समीक्षाओं
    0.46
     actionPerformed
    0.45
    पया
    0.45
     Signalez
    0.44
     crops
    0.43
    Activations Density 0.163%

    No Known Activations