© 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. 20-GEMMASCOPE-RES-16K
    11. 91
    Prev
    Next
    INDEX
    Explanations

    references to individuals and their relationships

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

    Follows a person's name or pronoun

    np_acts-logits-general · gemini-2.0-flash

    people, individuals, groups

    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
     *
    -0.61
    ].)
    -0.60
    —”
    -0.60
    orthand
    -0.59
    isla
    -0.56
    PhysRevLett
    -0.56
     ()
    -0.56
    \}^{
    -0.55
    *
    -0.55
    selas
    -0.55
    POSITIVE LOGITS
     advices
    0.81
    RenderAtEndOf
    0.79
    SourceChecksum
    0.77
     كومونز
    0.76
     resourceCulture
    0.75
     quitted
    0.72
     angekommen
    0.69
    ValueGeneration
    0.68
     Sedangkan
    0.68
     Apabila
    0.68
    Activations Density 0.321%

    No Known Activations