© 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. 20-GEMMASCOPE-RES-16K
    6. 6060
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate high degrees of quality or performance in various contexts

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

    Text after specific tokens ("forgotten," "from", etc.)

    np_acts-logits-general · gemini-2.0-flash

    possessive pronouns

    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
    Not in Any Lists

    No Comments

    Negative Logits
     resourceCulture
    -1.21
     typelib
    -1.10
    oredCriteria
    -1.08
    StoryboardSegue
    -1.06
    webElementXpaths
    -1.06
    DoubleQuotes
    -1.06
    +#+#
    -1.03
     AssemblyCulture
    -0.98
    MigrationBuilder
    -0.96
    IndentedString
    -0.94
    POSITIVE LOGITS
     celui
    0.80
     celle
    0.73
     celles
    0.61
     ones
    0.58
    jenige
    0.57
     yours
    0.56
     theirs
    0.50
     ours
    0.48
    même
    0.47
     others
    0.47
    Activations Density 0.943%

    No Known Activations