© 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. 8712
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the absence or negation of something

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

    absence of limitations or negative consequences

    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
     jouet
    -0.52
    HomeAsUpEnabled
    -0.50
     Offisielt
    -0.49
     suivante
    -0.49
     suivantes
    -0.46
     connexe
    -0.45
     suivants
    -0.45
    ArrowToggle
    -0.44
     Artículos
    -0.44
     "}";
    -0.44
    POSITIVE LOGITS
     without
    0.81
    without
    0.68
     tanpa
    0.60
     WITHOUT
    0.60
     ohne
    0.60
    Without
    0.59
     Without
    0.59
    Ohne
    0.55
     not
    0.54
     senza
    0.54
    Activations Density 0.022%

    No Known Activations