© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 4210
    Prev
    Next
    INDEX
    Explanations

    terms related to biological processes and mechanisms, particularly those involving steps and enzymes in pathways

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    masing
    -0.50
    CheckedChanged
    -0.44
     alternate
    -0.44
    nanoTime
    -0.44
     timeval
    -0.44
    slidesPer
    -0.43
     supplement
    -0.43
     imper
    -0.42
    gie
    -0.42
     konkur
    -0.41
    POSITIVE LOGITS
     stages
    1.02
     étape
    0.96
    étape
    0.94
     stage
    0.92
     Stage
    0.87
     STAGE
    0.85
    Stage
    0.83
     steps
    0.82
     Stages
    0.80
     Schritt
    0.77
    Activations Density 0.975%

    No Known Activations