© 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. 80406
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or operations involving negative and positive values

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

    negative signs and parentheses

    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
     InputDecoration
    -0.74
    Derbyniad
    -0.73
    StructEnd
    -0.69
     Autorizaciones
    -0.63
    Tikang
    -0.60
    AutoScaleMode
    -0.60
    jména
    -0.59
     censiti
    -0.57
     Waſſer
    -0.57
     ब्रेकडाउन
    -0.57
    POSITIVE LOGITS
    GenerationType
    0.29
    MigrationBuilder
    0.28
     mat
    0.28
    Javadoc
    0.28
     Levante
    0.27
     ibu
    0.27
     Gia
    0.27
    大人
    0.26
     against
    0.26
     food
    0.26
    Activations Density 0.293%

    No Known Activations