© 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. 9-GEMMASCOPE-RES-131K
    11. 77987
    Prev
    Next
    INDEX
    Explanations

    mentions of affected groups, whether they be individuals, vehicles, tissues, or populations

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

    who or what is affected

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    entrevista
    -0.32
     entrevista
    -0.32
     Entwurf
    -0.31
     itulah
    -0.31
    ujete
    -0.29
     acuerdos
    -0.29
     rychle
    -0.29
     которую
    -0.29
    setFirstName
    -0.29
     inilah
    -0.28
    POSITIVE LOGITS
     affected
    2.03
     Affected
    1.98
    Affected
    1.89
    affected
    1.89
     impacted
    1.44
     afectados
    1.26
     afectada
    1.23
     afectadas
    1.23
     unaffected
    1.22
     afectado
    1.22
    Activations Density 0.015%

    No Known Activations