Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 1463
    Prev
    Next
    INDEX
    Explanations

    references to agents and agency in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "agent" and its plural form

    np_acts-logits-general · gemini-2.0-flash

    agent and agency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Leck
    -0.71
     Quir
    -0.69
    มิ
    -0.66
     Tir
    -0.66
    ULI
    -0.65
    __*/
    -0.65
     Mú
    -0.63
     joi
    -0.63
    Tir
    -0.62
     Ahi
    -0.62
    POSITIVE LOGITS
     agents
    1.54
     Agents
    1.45
    Agents
    1.43
     agent
    1.40
    agents
    1.40
    AGENT
    1.37
     AGENT
    1.34
     Agent
    1.34
     AGENCY
    1.34
     AGENTS
    1.34
    Activations Density 0.119%

    No Known Activations