© 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. 12-GEMMASCOPE-RES-16K
    11. 5696
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and structures within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InstanceState
    -0.60
     itself
    -0.58
     herself
    -0.57
    MathML
    -0.56
    ExecuteReader
    -0.52
     Tapia
    -0.52
     themselves
    -0.52
     wikipagina
    -0.51
     himself
    -0.50
    itself
    -0.50
    POSITIVE LOGITS
    postsleuth
    0.72
    хьтан
    0.58
     ModelExpression
    0.56
    نمای
    0.52
    انتهای
    0.52
    "":
    0.51
    ConfigureAwait
    0.48
    ۣ
    0.47
    変な
    0.47
     صدای
    0.45
    Activations Density 1.239%

    No Known Activations