© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 10723
    Prev
    Next
    INDEX
    Explanations

    keywords related to programming constructs and methods

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

    Code-related tokens after specific keywords

    np_acts-logits-general · gemini-2.0-flash

    code identifiers and variable names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     even
    -0.44
     même
    -0.43
    </u>
    -0.42
     –
    -0.42
    </h2>
    -0.42
    ]['
    -0.41
    </b>
    -0.40
    ]][
    -0.40
    </i>
    -0.40
    ++){
    -0.39
    POSITIVE LOGITS
    AsUp
    0.85
     utafitiHapana
    0.83
    mybatisplus
    0.81
    migrationBuilder
    0.80
    RegressionTest
    0.80
     neceff
    0.79
     himſelf
    0.78
     ſever
    0.78
    ^(@)
    0.77
     purpoſe
    0.77
    Activations Density 0.134%

    No Known Activations