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. 17-GEMMASCOPE-RES-65K
    6. 28466
    Prev
    Next
    INDEX
    Explanations

    phrases related to wandering or movement through spaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_65k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ril
    -0.52
    FunctionFlags
    -0.52
     lift
    -0.49
     elevator
    -0.49
    BagConstraints
    -0.48
    rite
    -0.48
    staticmethod
    -0.47
    chid
    -0.47
     position
    -0.46
    strm
    -0.46
    POSITIVE LOGITS
    BeginInit
    0.67
    mybatisplus
    0.63
     ویکی‌پدی
    0.63
     ProtoMessage
    0.59
     مرئيه
    0.58
    AutoScale
    0.57
    CompleteListener
    0.57
    IsPostBack
    0.56
     فقال
    0.56
     Drapeau
    0.56
    Activations Density 0.028%

    No Known Activations