© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 354
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly periods and commas

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

    punctuation marks that signify the end of sentences

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

    preceding conjunctions and pronouns

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    artamento
    -0.57
    unggulan
    -0.56
    Dazu
    -0.56
    में
    -0.55
    satunya
    -0.53
    それは
    -0.52
    imte
    -0.50
    />";
    -0.50
    koliv
    -0.50
     calendriers
    -0.50
    POSITIVE LOGITS
     Together
    1.17
    Together
    1.15
     who
    1.10
     whom
    1.08
    together
    1.02
     together
    1.01
    RenderAtEndOf
    0.99
    whom
    0.95
    whose
    0.93
     whose
    0.90
    Activations Density 0.149%

    No Known Activations