Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15630
    Prev
    Next
    INDEX
    Explanations

    references to political titles and roles

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

    Position or title followed by a name

    np_acts-logits-general · gemini-2.0-flash

    deputy vice president

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     kasarigan
    -0.56
    SourceChecksum
    -0.49
    المكان
    -0.47
     <=",
    -0.46
    局长
    -0.43
    ebilir
    -0.43
    Rhestr
    -0.42
    皇帝
    -0.40
     chande
    -0.40
    Vidite
    -0.40
    POSITIVE LOGITS
     vice
    1.25
     Vice
    1.21
    Vice
    1.18
    副
    1.06
    vice
    1.02
     deputy
    1.00
     Deputy
    0.95
    Deputy
    0.93
     副
    0.91
     vicepresidente
    0.82
    Activations Density 0.110%

    No Known Activations