© 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. 22-GEMMASCOPE-RES-16K
    11. 8271
    Prev
    Next
    INDEX
    Explanations

    titles and roles associated with professional and academic expertise

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

    Occupations or roles

    np_acts-logits-general · gemini-2.0-flash

    professions and their descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -1.01
    +#+#
    -1.00
    AddTagHelper
    -0.97
    Tembelea
    -0.90
     Administrativna
    -0.86
    MigrationBuilder
    -0.83
    Diweddarwch
    -0.81
     AssemblyCulture
    -0.81
    SBATCH
    -0.81
     gynhyrchwyd
    -0.79
    POSITIVE LOGITS
     who
    1.07
     extraordinaire
    0.85
     specializing
    0.80
     working
    0.74
     turned
    0.73
     specialising
    0.73
     whom
    0.72
    /
    0.70
     manqué
    0.70
     whose
    0.67
    Activations Density 0.397%

    No Known Activations