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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 8870
    Prev
    Next
    INDEX
    Explanations

    words specifically related to "hats"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Marianne
    -0.37
     Mannes
    -0.37
    bedo
    -0.37
     Pang
    -0.35
    SharedDtor
    -0.35
    emang
    -0.35
     液
    -0.35
     cis
    -0.35
     Cis
    -0.34
     Ajax
    -0.34
    POSITIVE LOGITS
     hat
    4.13
     Hat
    3.70
    Hat
    3.58
     hats
    3.30
     HAT
    3.09
    hat
    3.00
     Hats
    2.86
    HAT
    2.73
    Hats
    2.61
    hats
    2.50
    Activations Density 0.177%

    No Known Activations