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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 6-GEMMASCOPE-RES-16K
    6. 12238
    Prev
    Next
    INDEX
    Explanations

    references to agents and agency in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/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.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Krie
    -0.74
    Lili
    -0.73
     SWR
    -0.72
     battleship
    -0.71
     Lasso
    -0.71
    prehension
    -0.71
     bifur
    -0.70
    ths
    -0.70
     Leck
    -0.69
     bifurcation
    -0.69
    POSITIVE LOGITS
     agents
    2.30
     Agents
    2.23
     agent
    2.20
     Agent
    2.14
    Agents
    2.10
    Agent
    2.07
     AGENT
    2.03
    agents
    1.99
     AGENTS
    1.97
    agent
    1.94
    Activations Density 0.064%

    No Known Activations