© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 11715
    Prev
    Next
    INDEX
    Explanations

    attributes related to softness and tactile qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     number
    -0.44
     vectorielles
    -0.44
     eventId
    -0.43
     thrombosis
    -0.43
     ſind
    -0.41
     pneus
    -0.41
     vícti
    -0.40
     rius
    -0.40
     galax
    -0.40
     activity
    -0.40
    POSITIVE LOGITS
     soft
    1.56
    soft
    1.50
     Soft
    1.47
     SOFT
    1.43
    Soft
    1.38
     softness
    1.32
     soften
    1.30
     softens
    1.30
    SOFT
    1.30
     softer
    1.29
    Activations Density 0.130%

    No Known Activations