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 - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 56970
    Prev
    Next
    INDEX
    Explanations

    instances of the term "bos" or the beginning of a new section 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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     itſelf
    -0.62
    Datuak
    -0.60
     оригіналу
    -0.57
    erals
    -0.54
    存于互联网档案馆
    -0.54
    +#+
    -0.54
    󠁮
    -0.53
    __*/
    -0.52
     iſt
    -0.52
     ſever
    -0.52
    POSITIVE LOGITS
    faßt
    0.61
     kasarigan
    0.61
     Anzeigen
    0.58
     himself
    0.57
     totul
    0.57
     собою
    0.56
    localize
    0.56
    kháu
    0.55
     rents
    0.53
    admin
    0.52
    Activations Density 0.000%

    No Known Activations