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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 2954
    Prev
    Next
    INDEX
    Explanations

    discussions about weight loss and health-related choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ligiloj
    -0.56
    orkel
    -0.48
    RTHOOK
    -0.47
     zü
    -0.47
    
    -0.47
     CURLOPT
    -0.46
    IsContent
    -0.44
     Einf
    -0.44
     vole
    -0.44
    EndGlobalSection
    -0.44
    POSITIVE LOGITS
     health
    0.42
     habet
    0.41
    ChildScrollView
    0.41
    health
    0.38
     Inscrivez
    0.37
     Health
    0.37
     neón
    0.36
    Билгалдахарш
    0.36
     fighter
    0.35
     saúde
    0.35
    Activations Density 0.325%

    No Known Activations