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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 15107
    Prev
    Next
    INDEX
    Explanations

    customizable services and options in culinary and business contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ngdoc
    -0.38
    })();
    
    -0.36
    intenant
    -0.35
     Beiträge
    -0.35
    Trending
    -0.35
    órios
    -0.35
     Wahrheit
    -0.34
     tendency
    -0.34
     चीज़ों
    -0.34
     beira
    -0.33
    POSITIVE LOGITS
     request
    0.77
     requests
    0.77
     requested
    0.71
     Request
    0.68
     customizations
    0.68
     customization
    0.68
     custom
    0.66
     Custom
    0.63
     REQUEST
    0.62
     requesting
    0.61
    Activations Density 0.131%

    No Known Activations