© 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. 20-GEMMASCOPE-RES-16K
    6. 11983
    Prev
    Next
    INDEX
    Explanations

    elements related to fear, paranoia, and the unnatural

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.65
    styleType
    -0.56
    mybatisplus
    -0.56
    httphttps
    -0.56
     artigian
    -0.54
    🇶
    -0.54
     transfieras
    -0.53
     FontWeight
    -0.52
     coraggio
    -0.52
     trám
    -0.51
    POSITIVE LOGITS
     creepy
    0.61
     eerie
    0.60
     sinister
    0.56
    creepy
    0.50
     omin
    0.48
     ominous
    0.46
    Creepy
    0.43
     inquiet
    0.42
     menacing
    0.42
     uncanny
    0.42
    Activations Density 0.176%

    No Known Activations