© 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. 31-GEMMASCOPE-RES-131K
    6. 44072
    Prev
    Next
    INDEX
    Explanations

    technical programming terminology and file-related references

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

    emulation

    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
     AssemblyCompany
    -0.58
     Siri
    -0.48
     GoogleFonts
    -0.47
     FetchType
    -0.47
    niſſe
    -0.47
    
    -0.46
    隈
    -0.46
    principalColumn
    -0.46
    styleType
    -0.45
    aarrggbb
    -0.44
    POSITIVE LOGITS
     emulator
    0.97
     emulation
    0.89
     em
    0.78
     emulate
    0.77
     Emulator
    0.77
     retro
    0.56
     Em
    0.56
     emu
    0.54
     Retro
    0.54
     nostalgic
    0.53
    Activations Density 0.036%

    No Known Activations