© 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. 12598
    Prev
    Next
    INDEX
    Explanations

    terms related to emotional responses and attitudes, particularly surrounding pity and skewness

    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
    躇
    -0.65
    ClientRect
    -0.60
    TacToe
    -0.57
     Souha
    -0.54
    bellar
    -0.54
     AppCompatTheme
    -0.54
    viel
    -0.53
     Grecian
    -0.52
    पूर्ण
    -0.52
    Wr
    -0.52
    POSITIVE LOGITS
    +:+
    0.74
    sulf
    0.69
    </thead>
    0.67
    nestjs
    0.64
     deed
    0.61
    PutMapping
    0.61
     sulfate
    0.60
    titleMargin
    0.60
    alogy
    0.60
    semantics
    0.60
    Activations Density 0.083%

    No Known Activations