© 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. 889
    Prev
    Next
    INDEX
    Explanations

    terms related to mitochondrial activity and function

    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
     resourceCulture
    -0.77
     Howe
    -0.74
    tagext
    -0.74
    illoma
    -0.68
    MigrationBuilder
    -0.67
     surla
    -0.67
    Francesca
    -0.66
    SequentialGroup
    -0.66
    AndEndTag
    -0.65
     Cáceres
    -0.65
    POSITIVE LOGITS
     Mit
    2.80
     mit
    2.72
    Mit
    2.67
    mit
    2.29
     MIT
    2.02
    MIT
    1.83
     Mitchell
    1.70
     MITCHELL
    1.67
    Mitchell
    1.52
     Mitch
    1.51
    Activations Density 0.066%

    No Known Activations