© 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. 2517
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly periods

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

    Follows a period

    np_acts-logits-general · gemini-2.0-flash

    various languages and styles

    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
    OrBuilder
    -0.59
    </>
    -0.54
    NUMX
    -0.54
    glGen
    -0.52
     seyn
    -0.51
     ſeveral
    -0.50
     coté
    -0.50
     $_"
    -0.49
    ^(@)
    -0.49
     iconFacebook
    -0.49
    POSITIVE LOGITS
     kasarigan
    0.96
     betweenstory
    0.64
     Réponses
    0.62
    hyrchwyd
    0.58
    LabelTagHelper
    0.57
     NSCoder
    0.57
     nakalista
    0.55
    󠁴
    0.55
    DIPSETTING
    0.54
    Kjelder
    0.54
    Activations Density 0.065%

    No Known Activations