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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 7202
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "early" occurrences or actions

    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
    Hochspringen
    -0.76
    Skocz
    -0.75
     GenerationType
    -0.71
    ɵɵ
    -0.67
     Савезне
    -0.65
    ="@+
    -0.63
     ISBN
    -0.62
     विश्वसनीयता
    -0.62
     intptr
    -0.62
    Lähteet
    -0.58
    POSITIVE LOGITS
    early
    1.74
    Early
    1.73
     Early
    1.66
     early
    1.60
     EARLY
    1.59
    EARLY
    1.45
    早
    1.27
     früh
    1.09
    早期
    1.07
     ран
    1.05
    Activations Density 0.083%

    No Known Activations