© 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-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 3134
    Prev
    Next
    INDEX
    Explanations

    mentions of agents and their roles or relationships

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

    "agent" or "agents"

    np_acts-logits-general · gemini-2.0-flash

    entity acting as an agent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atmosphère
    -0.61
     ujednoznacz
    -0.58
    épaisseur
    -0.56
     Públicas
    -0.53
     tuturor
    -0.52
     afgelopen
    -0.51
     estekak
    -0.50
     Noviembre
    -0.50
     olympique
    -0.50
    équilibre
    -0.49
    POSITIVE LOGITS
     agent
    2.63
     Agent
    2.55
    Agent
    2.52
    agent
    2.48
     agents
    2.44
     Agents
    2.42
     AGENT
    2.39
    Agents
    2.25
    AGENT
    2.14
     AGENTS
    2.13
    Activations Density 0.219%

    No Known Activations