© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 9988
    Prev
    Next
    INDEX
    Explanations

    elements related to assembly versioning and programming constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/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.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    barung
    -0.37
     sèche
    -0.34
    Tracce
    -0.32
     retribu
    -0.32
    BoxLayout
    -0.32
     altså
    -0.30
    Closure
    -0.29
     kalın
    -0.29
     necesariamente
    -0.28
    cense
    -0.28
    POSITIVE LOGITS
    
    0.86
    endphp
    0.73
    ngdoc
    0.70
     AssemblyVersion
    0.69
     BATH
    0.64
     TestBed
    0.63
     ModelRenderer
    0.62
     unsteady
    0.61
     bath
    0.59
     rainbows
    0.58
    Activations Density 1.647%

    No Known Activations