© 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. 33-GEMMASCOPE-RES-16K
    11. 11155
    Prev
    Next
    INDEX
    Explanations

    actions and states of execution in coding or programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Obrázky
    -0.56
    Tembelea
    -0.55
    OGND
    -0.50
    awtextra
    -0.47
     nct
    -0.47
    CloseOperation
    -0.47
     acon
    -0.47
    inib
    -0.46
    DeleteBehavior
    -0.46
    WriteTagHelper
    -0.46
    POSITIVE LOGITS
    Letting
    0.46
     Letting
    0.43
     letting
    0.40
     corretto
    0.38
     laten
    0.37
    Bringing
    0.36
     causing
    0.36
    routeProvider
    0.35
    letting
    0.35
     caused
    0.34
    Activations Density 0.099%

    No Known Activations