Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 10881
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their frequency in the text

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

    Tokens after commas that introduce contrasting information

    np_acts-logits-general · gemini-2.0-flash

    contrast and continuation

    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
    ,
    -0.94
    …
    -0.76
    「
    -0.73
    ...
    -0.69
    ?
    -0.64
    .
    -0.63
    :
    -0.60
    『
    -0.59
    '
    -0.59
    /
    -0.55
    POSITIVE LOGITS
     etc
    1.16
     however
    1.11
     }}$,
    1.07
     albeit
    0.99
     namely
    0.91
     including
    0.90
     which
    0.89
     yaitu
    0.89
    =,
    0.89
     though
    0.88
    Activations Density 2.749%

    No Known Activations