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. 16215
    Prev
    Next
    INDEX
    Explanations

    key terms and phrases related to data analysis and personal expression

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

    Follows a verb, often "to be"

    np_acts-logits-general · gemini-2.0-flash

    programming jargon or terms

    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
     {
    
    
    -0.40
    ();
    
    
    -0.39
     المعيارى
    -0.38
    DataAnnotations
    -0.35
    );
    
    
    -0.32
    ATEGY
    -0.32
     gerakan
    -0.30
    
    -0.30
     */
    
    
    -0.30
    });
    
    
    -0.30
    POSITIVE LOGITS
    uxxxx
    1.40
    InjectAttribute
    1.16
    weightedMode
    1.00
    InstrumentedTest
    0.85
    .*")]
    0.73
     GenerationType
    0.64
    autoreleasepool
    0.57
    parsedMessage
    0.55
     MemoryStream
    0.54
     yyhl
    0.54
    Activations Density 1.030%

    No Known Activations