© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 11260
    Prev
    Next
    INDEX
    Explanations

    terms related to professional titles and roles

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

    Titles such as president, director, editor, or officer

    np_acts-logits-general · gemini-2.0-flash

    high-ranking job titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -1.08
    CloseOperation
    -1.00
     ModelExpression
    -0.96
     MainAxisSize
    -0.96
     tartalomajánló
    -0.95
    ConstraintMaker
    -0.90
     дописавши
    -0.89
     gynhyrchwyd
    -0.87
    RTEE
    -0.82
    adə
    -0.81
    POSITIVE LOGITS
     at
    0.79
     for
    0.74
     of
    0.68
     designate
    0.54
     and
    0.53
     from
    0.52
     presso
    0.50
     emeritus
    0.48
     fondateur
    0.45
     with
    0.44
    Activations Density 0.124%

    No Known Activations