© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 4024
    Prev
    Next
    INDEX
    Explanations

    phrases related to recruitment and team composition

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

    Follows pronouns or proper nouns

    np_acts-logits-general · gemini-2.0-flash

    we find

    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
    Testimonial
    -0.60
    LabelTagHelper
    -0.57
    SharedDtor
    -0.52
    SharedCtor
    -0.50
    NamedQueries
    -0.49
     REFERENCES
    -0.49
     dags
    -0.47
     Referenzen
    -0.46
    weer
    -0.46
    annie
    -0.46
    POSITIVE LOGITS
     coverage
    0.71
    Reaction
    0.69
    \{\\
    0.68
    ">//
    0.68
     Coverage
    0.67
     reaction
    0.67
    MigrationBuilder
    0.66
    Coverage
    0.66
     Reaction
    0.65
    rungsseite
    0.65
    Activations Density 0.167%

    No Known Activations