© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 119781
    Prev
    Next
    INDEX
    Explanations

    terms related to agents and their organizational structures

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

    agent and agentpool

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    Fernseh
    -0.32
     hinaus
    -0.31
     geliefert
    -0.31
    |)
    -0.30
     Verwendung
    -0.30
     erhältlich
    -0.29
     feitos
    -0.28
     Verfügung
    -0.28
    smöglichkeiten
    -0.28
     Genehmigung
    -0.28
    POSITIVE LOGITS
    agent
    1.87
    Agent
    1.86
     Agent
    1.72
     AGENT
    1.58
     agent
    1.57
    AGENT
    1.53
     Agents
    1.51
    Agents
    1.48
    agents
    1.43
     agents
    1.37
    Activations Density 0.005%

    No Known Activations