© 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. 15955
    Prev
    Next
    INDEX
    Explanations

    code related to the Gulp task automation tool

    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
    BottomSheet
    -0.51
     xoay
    -0.49
    protoimpl
    -0.45
    findOneAndUpdate
    -0.45
    MutableLiveData
    -0.44
    strconv
    -0.43
    EndContext
    -0.42
    referrer
    -0.42
     ثبت
    -0.41
    itattu
    -0.40
    POSITIVE LOGITS
    يميديا
    0.68
    сылкі
    0.67
    новниш
    0.63
     Hopf
    0.61
     Nazare
    0.61
     Shaksp
    0.59
    ValueStyle
    0.58
     flamma
    0.58
     Palae
    0.58
     Pent
    0.57
    Activations Density 0.025%

    No Known Activations