© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 5864
    Prev
    Next
    INDEX
    Explanations

    references to groups of people, their relationships, and the complexities surrounding societal structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PrototypeOf
    -0.50
    ridae
    -0.45
     eventual
    -0.45
    vants
    -0.45
    verzeichnis
    -0.43
     Wartawan
    -0.42
    Réalisation
    -0.42
    zzleHttp
    -0.42
    resave
    -0.40
    closedir
    -0.40
    POSITIVE LOGITS
     previously
    3.02
     Previously
    2.81
    Previously
    2.72
     formerly
    2.72
    previously
    2.70
     heretofore
    2.44
     auparavant
    2.30
     Formerly
    2.27
     anteriormente
    2.25
    formerly
    2.23
    Activations Density 1.175%

    No Known Activations