© 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. 2-GEMMASCOPE-RES-16K
    6. 6967
    Prev
    Next
    INDEX
    Explanations

    terms related to protocols and classic concepts in technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Xna
    -0.82
     susun
    -0.69
     متعلقه
    -0.69
    alucía
    -0.65
     Signalez
    -0.64
     useSelector
    -0.62
    ActivityResult
    -0.61
    uidado
    -0.60
     handling
    -0.59
    onActivityResult
    -0.59
    POSITIVE LOGITS
    buf
    0.88
     Protocol
    0.79
     protocol
    0.77
     buf
    0.75
     Classic
    0.73
     classic
    0.73
     PLATES
    0.72
     CLASSIC
    0.71
    protocols
    0.70
    protocol
    0.70
    Activations Density 0.046%

    No Known Activations