© 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. 7771
    Prev
    Next
    INDEX
    Explanations

    SQL commands and their components

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

    SQL "SELECT" statements or clauses

    np_acts-logits-general · gemini-2.0-flash

    select statement

    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
    RegressionTest
    -0.71
     autorytatywna
    -0.70
    intios
    -0.50
    تقاوى
    -0.49
     समीक्षाओं
    -0.47
    RenderAtEndOf
    -0.46
    UpInside
    -0.46
    principalColumn
    -0.46
     économiques
    -0.45
     <>",
    -0.45
    POSITIVE LOGITS
    select
    0.64
     select
    0.59
    SELECT
    0.59
    Select
    0.50
     SELECT
    0.48
     Select
    0.46
    __(/*!
    0.43
     BoxDecoration
    0.42
    __*/
    0.42
     SPO
    0.42
    Activations Density 0.210%

    No Known Activations