Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 7725
    Prev
    Next
    INDEX
    Explanations

    SQL-related queries and commands

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

    SQL queries and statements

    np_acts-logits-general · gemini-2.0-flash

    SQL keywords and clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    •SQL-labeled features

    No Comments

    Negative Logits
     nahilalakip
    -0.87
    enumi
    -0.50
    QMetaType
    -0.49
    xture
    -0.48
    ́ng
    -0.45
    netbeans
    -0.45
    XmlAccessorType
    -0.44
    heide
    -0.44
     silk
    -0.44
    PONENT
    -0.44
    POSITIVE LOGITS
    where
    0.96
     where
    0.92
    Where
    0.90
     WHERE
    0.87
     Where
    0.84
    WHERE
    0.84
     SELECT
    0.82
     select
    0.77
     query
    0.76
    SELECT
    0.76
    Activations Density 0.394%

    No Known Activations