© 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
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 682
    Prev
    Next
    INDEX
    Explanations

    terms related to insurance coverage and premium calculations

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

    words related to recommendations, suggestions, or calls to action in promotional or instructional content.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     protoimpl
    -0.46
     Италијани
    -0.45
     adopted
    -0.45
    팎
    -0.43
     disbanded
    -0.43
     Italijanski
    -0.42
    extré
    -0.41
     Schuster
    -0.41
     forgiven
    -0.41
     adopting
    -0.41
    POSITIVE LOGITS
     utafitiHapana
    0.69
     betweenstory
    0.57
    CloseOperation
    0.50
     للمعارف
    0.44
    fromnode
    0.43
    contentLoaded
    0.42
     jspb
    0.42
     "..\..\..\
    0.41
     dedans
    0.41
     snippetHide
    0.40
    Activations Density 0.078%

    No Known Activations