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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 15258
    Prev
    Next
    INDEX
    Explanations

    specific actions or descriptions involving physical interactions or manipulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     FetchType
    -0.60
     <<<<<<<<<<<<<<
    -0.58
    setVerticalGroup
    -0.54
    createCell
    -0.53
     שוליים
    -0.53
     跳转至
    -0.51
    atguigu
    -0.51
    CodedInputStream
    -0.48
    interopRequire
    -0.48
    脚注の使い方
    -0.47
    POSITIVE LOGITS
     thrust
    0.68
    thrust
    0.66
     inserted
    0.64
    插入
    0.60
    الإنجليزية
    0.60
     plugged
    0.59
    ScopeManager
    0.59
     插入
    0.57
    plugged
    0.56
    拿出
    0.56
    Activations Density 0.461%

    No Known Activations