© 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. 20
    Prev
    Next
    INDEX
    Explanations

    instances of possessive pronouns or possessive constructions

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

    Follows punctuation or uncommon symbols

    np_acts-logits-general · gemini-2.0-flash

    mathematical or scientific notation

    np_acts-logits-general · gemini-2.5-flash-lite

    The marked tokens represent contractions where an apostrophe is elided or appears in contexts where it marks the abbreviated form of "not" or possessive pronouns (e.g., "hadn't," "didn't," "I'm," "shouldn't," "wasn't"). These represent standard English contraction patterns in narrative and conversational text.

    eleuther_acts_top20 · claude-4-5-haikuTriggered by @kparkhamchuk
    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
     AssemblyTitle
    -0.70
     Signalez
    -0.61
    baomidou
    -0.53
    dymyr
    -0.49
    quel
    -0.49
    RequiresApi
    -0.49
     onOptions
    -0.48
    contentLoaded
    -0.48
     WebDriverWait
    -0.48
    alibaba
    -0.47
    POSITIVE LOGITS
     Diſ
    0.67
     ſon
    0.60
     Conſ
    0.59
     Daß
    0.58
     reaſon
    0.58
     Reſ
    0.57
     moſt
    0.56
     diſt
    0.56
    —“
    0.55
    ”—
    0.55
    Activations Density 0.157%

    No Known Activations