© 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. 79230
    Prev
    Next
    INDEX
    Explanations

    references to detailed information or varying levels of specificity

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

    detail

    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
     ſind
    -0.73
     Económica
    -0.71
     femininas
    -0.67
     engraçadas
    -0.66
     Inscrivez
    -0.65
     ChromeDriver
    -0.63
    UserScript
    -0.62
    principalColumn
    -0.62
     Italijani
    -0.61
     ainfi
    -0.60
    POSITIVE LOGITS
     Detail
    1.16
     detail
    1.15
     details
    1.11
    detail
    1.06
     Details
    1.06
     DETAIL
    1.02
    Detail
    1.02
    details
    0.98
    Details
    0.92
     DETAILS
    0.88
    Activations Density 0.021%

    No Known Activations