© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 11591
    Prev
    Next
    INDEX
    Explanations

    formatted output statements in code, particularly those that use placeholders for variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.67
    CloseOperation
    -0.61
    AnchorTagHelper
    -0.57
    Хьажоргаш
    -0.56
    UrlResolution
    -0.55
    >--}}
    -0.55
     يتيمه
    -0.53
    Наводи
    -0.52
    Халык
    -0.52
    tvguidetime
    -0.50
    POSITIVE LOGITS
     %
    0.35
    d
    0.35
    Todd
    0.33
    dragen
    0.33
     ibunya
    0.33
     placas
    0.32
     Alters
    0.32
     Flucht
    0.31
     Grimes
    0.31
    Luong
    0.31
    Activations Density 0.152%

    No Known Activations