© 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. 28-GEMMASCOPE-RES-16K
    11. 3792
    Prev
    Next
    INDEX
    Explanations

    references to variables or function names in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    The token "a" in code

    np_acts-logits-general · gemini-2.0-flash

    variable declarations and labels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    queles
    -0.77
    quilo
    -0.65
     Grüsse
    -0.64
    躇
    -0.49
     зато
    -0.49
     możli
    -0.49
    AndroidJUnit
    -0.47
     dlatego
    -0.47
    gerufen
    -0.45
    ladung
    -0.44
    POSITIVE LOGITS
    getA
    0.59
     A
    0.54
     PartialEq
    0.50
    SOA
    0.49
    A
    0.48
     aVar
    0.48
    fA
    0.46
    aaa
    0.46
    jsxFileName
    0.45
     bArr
    0.44
    Activations Density 0.523%

    No Known Activations