© 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. 21-GEMMASCOPE-RES-16K
    6. 9161
    Prev
    Next
    INDEX
    Explanations

    references to biological processes and mechanisms related to cellular functions and signaling pathways

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/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.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Teknik
    -0.61
     Teknik
    -0.60
     spirito
    -0.56
    Ety
    -0.56
     swab
    -0.56
     démoc
    -0.54
     Camacho
    -0.54
    atang
    -0.53
     swabs
    -0.53
     busto
    -0.52
    POSITIVE LOGITS
     mechanisms
    1.23
     mechanism
    1.20
     regulation
    1.05
     Mechanisms
    1.03
     Mechanism
    0.99
    mechanism
    0.98
     mecanismos
    0.93
     regulating
    0.92
     regulate
    0.91
    Mechanisms
    0.89
    Activations Density 3.126%

    No Known Activations