© 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. 0-GEMMASCOPE-RES-65K
    6. 10038
    Prev
    Next
    INDEX
    Explanations

    references to geographic or territorial names, indicating locations or landmarks

    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
     AttributeSet
    -0.69
    ImageContext
    -0.67
    脚注の使い方
    -0.66
     Rumi
    -0.65
     betweenstory
    -0.65
     válida
    -0.63
     utafitiHapana
    -0.63
    UnitTesting
    -0.63
    __":
    
    -0.63
     Anſ
    -0.63
    POSITIVE LOGITS
     Schar
    0.68
     Land
    0.63
    nh
    0.63
    plusplus
    0.58
    dag
    0.57
     nh
    0.54
    LAND
    0.54
    principalColumn
    0.54
     manual
    0.54
    lah
    0.54
    Activations Density 0.039%

    No Known Activations