© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14303
    Prev
    Next
    INDEX
    Explanations

    programming constructs and data structures used in coding

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

    Code syntax: structs, definitions, and types

    np_acts-logits-general · gemini-2.0-flash

    struct definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     queſta
    -0.81
    GraphicsUnit
    -0.79
     оригіналу
    -0.73
    principalColumn
    -0.73
    ьаж
    -0.73
     Meksiku
    -0.72
    ⟬
    -0.72
     ModelExpression
    -0.70
    󠁣
    -0.69
     <>",
    -0.68
    POSITIVE LOGITS
    setVerticalGroup
    0.57
    urlpatterns
    0.51
     following
    0.49
     suivantes
    0.48
    TestingModule
    0.47
    <thead>
    0.46
     suivante
    0.43
     berikut
    0.40
    如下
    0.40
     folgende
    0.40
    Activations Density 0.311%

    No Known Activations