© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 38489
    Prev
    Next
    INDEX
    Explanations

    references to specific models and features of vehicles

    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
     CreateTagHelper
    -0.46
    帖最后由
    -0.44
    出版年
    -0.44
     ello
    -0.43
    UnknownFieldSet
    -0.42
    الإنجليزية
    -0.41
     AssemblyProduct
    -0.41
    Hidden
    -0.41
     مشين
    -0.41
    atop
    -0.40
    POSITIVE LOGITS
     createContext
    0.71
    codable
    0.65
    XmlAccessorType
    0.62
     onPostExecute
    0.60
    StateToProps
    0.59
     préférence
    0.59
     према
    0.59
     StringTokenizer
    0.59
     intptr
    0.58
    classmethod
    0.57
    Activations Density 0.172%

    No Known Activations