© 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. 23255
    Prev
    Next
    INDEX
    Explanations

    phrases related to vaccination eligibility and demographic age groups

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

    children aged or those

    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
    copy
    -0.28
     wikihow
    -0.28
    GeoNames
    -0.27
     inception
    -0.26
    ciclopedia
    -0.26
    })();
    -0.26
    haya
    -0.25
    Succeed
    -0.25
     copy
    -0.24
     ikon
    -0.24
    POSITIVE LOGITS
     محفوظة
    0.82
    IntoConstraints
    0.75
    copg
    0.67
    AddTagHelper
    0.65
    énario
    0.63
    InputBorder
    0.62
    Referències
    0.62
    rungsseite
    0.60
     sanitaria
    0.59
    ghijklmnop
    0.59
    Activations Density 0.007%

    No Known Activations