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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 5237
    Prev
    Next
    INDEX
    Explanations

    expressions of dislike or animosity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    $('.
    -0.41
     ACE
    -0.39
    enderror
    -0.37
     calendriers
    -0.37
    ~/
    -0.36
    成就
    -0.35
    rlrl
    -0.35
    Géographie
    -0.34
     registros
    -0.34
    '][]
    -0.34
    POSITIVE LOGITS
     hate
    0.93
     Hate
    0.77
    Hate
    0.75
     dominate
    0.73
     dominated
    0.72
     HATE
    0.72
     hates
    0.72
    hate
    0.69
     dominates
    0.69
     domination
    0.68
    Activations Density 0.103%

    No Known Activations