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. 16-GEMMASCOPE-RES-16K
    6. 6141
    Prev
    Next
    INDEX
    Explanations

    the start of a text sequence or document format

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

    Punctuated section headers or titles

    np_acts-logits-general · gemini-2.0-flash

    judicial nominees

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     entanto
    -0.84
     obstante
    -0.82
     thromb
    -0.80
     SPIRIT
    -0.76
     SECUR
    -0.74
    ütü
    -0.74
     Ballard
    -0.71
     Plum
    -0.70
     pData
    -0.68
    genheit
    -0.68
    POSITIVE LOGITS
    '",
    0.82
    __*/
    0.81
    ",""
    0.81
    ")
    0.78
    '".
    0.78
    ]][
    0.78
    '"
    0.78
     Baillargeon
    0.77
    ":
    0.75
    ❤❤
    0.75
    Activations Density 0.145%

    No Known Activations