© 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. 31-GEMMASCOPE-RES-131K
    11. 91268
    Prev
    Next
    INDEX
    Explanations

    the concept of searching or discovering information

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

    fascinating or frustrating emotions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     برانيه
    -0.50
    SourceChecksum
    -0.40
    ׁ
    -0.34
    antMatchers
    -0.32
    cibly
    -0.32
     oprot
    -0.32
    jsonwebtoken
    -0.32
    たっぷり
    -0.32
    исленность
    -0.32
    Gön
    -0.31
    POSITIVE LOGITS
     interesting
    1.23
     fascinating
    1.23
     frustrating
    1.16
     intriguing
    1.15
     exciting
    1.15
     terrifying
    1.13
     scary
    1.13
     embarrassing
    1.13
    interesting
    1.12
     inconvenient
    1.10
    Activations Density 0.219%

    No Known Activations