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 - 65k
    5. 12-GEMMASCOPE-RES-65K
    6. 13655
    Prev
    Next
    INDEX
    Explanations

    the presence of the token "<bos>", indicating the beginning of a new section or thought

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     log
    -0.53
    nö
    -0.49
    ILog
    -0.47
     "
    -0.47
     use
    -0.47
     my
    -0.47
    ropy
    -0.46
     ("
    -0.44
     (
    -0.43
     sub
    -0.43
    POSITIVE LOGITS
    Tikang
    1.10
    TypedDataSet
    0.96
    abestanden
    0.94
     насељу
    0.93
    verwijspagina
    0.90
    Diwedd
    0.88
    WithIOException
    0.85
     Exacts
    0.85
    ########.
    0.85
    addCriterion
    0.83
    Activations Density 0.031%

    No Known Activations