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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 13-GEMMASCOPE-RES-16K
    6. 12322
    Prev
    Next
    INDEX
    Explanations

    indicators of a notable start or boundary in a narrative or document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵↵
    -0.93
    ↵
    -0.84
    .
    -0.70
    ,
    -0.68
     "
    -0.64
    ;
    -0.63
    :
    -0.62
     a
    -0.56
     (
    -0.56
    ↵↵↵↵
    -0.56
    POSITIVE LOGITS
    <bos>
    3.08
     Савезне
    1.65
    ItemBackground
    1.54
    WithIOException
    1.46
     Paglinawan
    1.42
     AspNetCore
    1.40
     мәкал
    1.36
     disambiguazione
    1.34
     виправивши
    1.34
     autorytatywna
    1.32
    Activations Density 0.002%

    No Known Activations