© 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. 31-GEMMASCOPE-RES-131K
    11. 65031
    Prev
    Next
    INDEX
    Explanations

    references to various sectors and industries involved in research, services, and client relationships

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

    business entities and clients

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CloseOperation
    -0.53
     gynhyrchwyd
    -0.49
    Життєпис
    -0.48
    MessageTagHelper
    -0.47
    //});
    -0.43
     mergeFrom
    -0.43
    },[
    -0.42
     Bumper
    -0.42
    RTDA
    -0.42
    Parcelize
    -0.42
    POSITIVE LOGITS
     clients
    0.97
     clientele
    0.87
    clients
    0.82
     needs
    0.80
    needs
    0.79
     customers
    0.79
     clientèle
    0.76
     Clients
    0.75
     clientes
    0.75
    customers
    0.72
    Activations Density 0.033%

    No Known Activations