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. 21-GEMMASCOPE-RES-16K
    6. 11756
    Prev
    Next
    INDEX
    Explanations

    the presence of questions or inquiries within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ThroughAttribute
    -0.58
    
    -0.47
    droje
    -0.46
    ACHUSET
    -0.45
     Bewußt
    -0.45
     Miß
    -0.43
     remercier
    -0.42
    resizingMask
    -0.42
     surla
    -0.42
     AssemblyCulture
    -0.41
    POSITIVE LOGITS
    providedIn
    0.50
    igshid
    0.50
    PostMapping
    0.47
     BorderRadius
    0.45
    +#+
    0.44
     ️
    0.44
    ',['
    0.44
    saraba
    0.44
    嘅
    0.43
    ️
    0.43
    Activations Density 0.147%

    No Known Activations