© 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. 12-GEMMASCOPE-RES-16K
    6. 10384
    Prev
    Next
    INDEX
    Explanations

    mentions of "agent" and its variations in terms of context, particularly in legal or formal scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewFeatures
    -0.91
    aarrggbb
    -0.89
     Hughes
    -0.83
    pewa
    -0.83
     Figueroa
    -0.83
    izophrenia
    -0.82
    verläs
    -0.81
    BIÉN
    -0.81
     Hickey
    -0.80
     BoxFit
    -0.80
    POSITIVE LOGITS
     Agents
    0.82
     AGENTS
    0.81
    est
    0.79
    Agents
    0.78
     Agent
    0.77
     crystall
    0.75
     Jol
    0.72
     AGENT
    0.71
    databind
    0.69
    ant
    0.69
    Activations Density 0.082%

    No Known Activations