© 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. 13-GEMMASCOPE-RES-16K
    6. 8639
    Prev
    Next
    INDEX
    Explanations

    references to programming terminology and technical specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     manos
    -0.32
     nhàng
    -0.32
     defaultstate
    -0.30
     grueso
    -0.29
    AnchorStyles
    -0.29
     orilla
    -0.28
    úrate
    -0.28
     discu
    -0.28
     quitter
    -0.28
    İstinadlar
    -0.27
    POSITIVE LOGITS
     Administrativna
    0.59
    ThroughAttribute
    0.52
    InputBorder
    0.52
    тябрь
    0.51
    gatsby
    0.51
    zzleHttp
    0.49
     otomatig
    0.48
     Perfon
    0.48
    maus
    0.48
    remont
    0.48
    Activations Density 1.458%

    No Known Activations