© 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. 7569
    Prev
    Next
    INDEX
    Explanations

    code structure and programming constructs in a programming language

    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
    独
    -0.34
     AppCompat
    -0.34
     heart
    -0.33
     protetor
    -0.33
     <>",
    -0.33
    ústria
    -0.31
    Heart
    -0.31
    ----------------
    -0.31
     build
    -0.31
     AppComponent
    -0.30
    POSITIVE LOGITS
    SharedCtor
    0.71
     utafitiHapana
    0.68
    SharedDtor
    0.63
     chofe
    0.61
    WireFormatLite
    0.59
    SequentialGroup
    0.58
    MetaObject
    0.57
    évaluateur
    0.54
     surla
    0.52
     pageNo
    0.50
    Activations Density 0.308%

    No Known Activations