© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 15787
    Prev
    Next
    INDEX
    Explanations

    code structures and expressions related to queries and conditions

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

    Occurrences before or after the word "query"

    np_acts-logits-general · gemini-2.0-flash

    query

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tvguidetime
    -0.59
    aarrggbb
    -0.52
    dce
    -0.47
     CVE
    -0.46
    lace
    -0.45
    nodoc
    -0.44
    christ
    -0.44
    INSTALLATION
    -0.43
     hippocampus
    -0.43
    脚注の使い方
    -0.42
    POSITIVE LOGITS
     query
    3.70
    query
    3.41
     Query
    3.08
    Query
    2.90
     queries
    2.69
    QUERY
    2.59
     QUERY
    2.52
     Queries
    2.35
     querying
    2.25
     queried
    2.21
    Activations Density 0.070%

    No Known Activations