© 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. 6-GEMMASCOPE-RES-16K
    6. 6473
    Prev
    Next
    INDEX
    Explanations

    emphatic expressions emphasizing importance or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    batis
    -0.69
     Arque
    -0.63
     Poz
    -0.63
     Schleswig
    -0.61
     Salim
    -0.61
     GIF
    -0.61
     Miki
    -0.59
     Dewey
    -0.59
     Fuku
    -0.58
     Pompey
    -0.58
    POSITIVE LOGITS
    Especially
    1.72
     Especially
    1.65
     especially
    1.64
    especially
    1.60
    pecially
    1.51
     Particularly
    1.44
     particularly
    1.36
    ticularly
    1.32
    particularly
    1.31
     ESPEC
    1.29
    Activations Density 0.074%

    No Known Activations