© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 0-GEMMASCOPE-RES-65K
    6. 10256
    Prev
    Next
    INDEX
    Explanations

    instances of the word "pushed" or its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __;
    -0.65
    脚注の使い方
    -0.59
    +#+#
    -0.58
    ainya
    -0.58
    ignal
    -0.57
    zaba
    -0.57
     colorWith
    -0.56
    AddTagHelper
    -0.54
     minne
    -0.54
    outSlope
    -0.54
    POSITIVE LOGITS
     push
    0.99
     pushed
    0.96
    pushed
    0.89
     pushes
    0.85
     يتيمه
    0.83
     PUSH
    0.80
     pushing
    0.76
    Pushing
    0.76
    push
    0.74
     Pushing
    0.73
    Activations Density 0.064%

    No Known Activations