© 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. 11-GEMMASCOPE-RES-16K
    11. 5493
    Prev
    Next
    INDEX
    Explanations

    programming-related function definitions and GPIO relay control actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CodeAttribute
    -0.52
    ngdoc
    -0.45
     noDo
    -0.44
     Autorizaciones
    -0.42
    InitVars
    -0.41
     Rast
    -0.41
     Dike
    -0.40
    ftagPool
    -0.40
     capital
    -0.40
    akos
    -0.40
    POSITIVE LOGITS
    tinyos
    0.47
    openConnection
    0.41
     devices
    0.41
     device
    0.38
    Jeografia
    0.38
    ExtendWith
    0.37
    utuhkan
    0.37
    amentlich
    0.36
     naudoti
    0.36
    دانشنامهٔ
    0.36
    Activations Density 0.949%

    No Known Activations