© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 13019
    Prev
    Next
    INDEX
    Explanations

    sentiments of mistrust and fear within the context of community interactions and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BindingResult
    -0.38
     Catawiki
    -0.38
     nhiệt
    -0.36
     samman
    -0.36
    SLO
    -0.36
    rodow
    -0.35
    torta
    -0.33
     fondu
    -0.33
     Loc
    -0.33
     Hinge
    -0.33
    POSITIVE LOGITS
     paranoia
    0.88
     fear
    0.85
     paranoid
    0.84
     fearing
    0.81
     afraid
    0.81
     fears
    0.80
    fear
    0.78
     Afraid
    0.75
    Fear
    0.75
     miedo
    0.74
    Activations Density 0.455%

    No Known Activations