© 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. 33-GEMMASCOPE-RES-16K
    6. 11827
    Prev
    Next
    INDEX
    Explanations

    elements related to code structure and programming syntax

    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
    tvguidetime
    -0.54
    writeHead
    -0.45
    InitVars
    -0.45
    InSection
    -0.44
    ScopeManager
    -0.43
    UnusedPrivate
    -0.41
    ftagPool
    -0.40
    TestingModule
    -0.40
    forChild
    -0.40
    msgSender
    -0.39
    POSITIVE LOGITS
     retrofit
    0.65
    retrofit
    0.59
     Retrofit
    0.58
    Retrofit
    0.57
    retro
    0.57
     Retro
    0.57
     retro
    0.54
    Retro
    0.54
     rétro
    0.53
     Dagger
    0.45
    Activations Density 0.288%

    No Known Activations