© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 10323
    Prev
    Next
    INDEX
    Explanations

    words related to lighting or brightness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 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
    قایناقلار
    -0.90
     صوتيه
    -0.81
    BagConstraints
    -0.80
    +#+#
    -0.78
     linkovi
    -0.77
     stiefel
    -0.76
     getItemId
    -0.76
     Pter
    -0.76
     randomNumber
    -0.75
    Pter
    -0.75
    POSITIVE LOGITS
     lit
    1.48
     Lit
    1.39
    Lit
    1.35
     LIT
    1.18
    lit
    1.15
    LIT
    1.04
     litter
    0.93
     LITER
    0.86
     Lite
    0.86
     Liter
    0.81
    Activations Density 0.169%

    No Known Activations