© 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. 39-GEMMASCOPE-RES-16K
    11. 1229
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to validation processes and conditional logic in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     intptr
    -0.41
     Wiktionnaire
    -0.36
    ècie
    -0.32
    SuspendLayout
    -0.32
    hoga
    -0.31
     quidem
    -0.31
    lação
    -0.30
    Legende
    -0.30
     kaarangay
    -0.29
    bė
    -0.29
    POSITIVE LOGITS
     otherwise
    4.53
     Otherwise
    4.16
    Otherwise
    4.06
    otherwise
    4.00
     OTHERWISE
    3.42
     altrimenti
    3.20
     sonst
    3.02
    否则
    2.98
     else
    2.95
     иначе
    2.92
    Activations Density 0.858%

    No Known Activations