© 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. 50220
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "hospitals" and "hostility."

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

    hostile, hostility

    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
     BNF
    -0.50
     للاسماء
    -0.49
     Goethe
    -0.48
     STC
    -0.47
    extAlignment
    -0.46
     inton
    -0.45
     CBN
    -0.44
     ACB
    -0.44
     APA
    -0.42
     EconPapers
    -0.42
    POSITIVE LOGITS
     Hos
    2.28
    Hos
    2.20
    hos
    1.98
     hos
    1.98
     HOS
    1.46
    HOS
    1.38
     hostile
    1.28
     HOST
    1.27
     hostility
    1.21
    host
    1.01
    Activations Density 0.005%

    No Known Activations