© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 0-GEMMASCOPE-RES-65K
    11. 9984
    Prev
    Next
    INDEX
    Explanations

    technical jargon and complex terminology

    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
     itſelf
    -1.39
    دانشنامهٔ
    -1.35
    BibitemShut
    -1.35
     myſelf
    -1.34
     Efq
    -1.32
    })`
    -1.27
    
    -1.27
    脚注の使い方
    -1.26
    ſelf
    -1.25
     незавершена
    -1.25
    POSITIVE LOGITS
    5
    4.06
    4
    2.63
    6
    2.42
    3
    2.30
    7
    2.23
    8
    2.05
    9
    2.02
    2
    2.02
    1
    1.92
    ５
    1.84
    Activations Density 0.804%

    No Known Activations