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. 5-GEMMASCOPE-RES-16K
    6. 12638
    Prev
    Next
    INDEX
    Explanations

    statements about actions, outcomes, or conditions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OneToOne
    -0.48
    vata
    -0.43
    iNdEx
    -0.41
     Aug
    -0.40
    NOPQRST
    -0.39
    Aug
    -0.37
     mej
    -0.37
     nip
    -0.36
     Jan
    -0.36
    calf
    -0.36
    POSITIVE LOGITS
    Datuak
    1.06
    出版年
    0.74
    parsedMessage
    0.72
    WithIOException
    0.69
    enumi
    0.68
    //
    0.68
    "?>
    0.68
     disambiguazione
    0.65
     utafitiHapana
    0.64
     {?}
    0.64
    Activations Density 0.703%

    No Known Activations