© 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. 3558
    Prev
    Next
    INDEX
    Explanations

    references to personal relationships and individual experiences

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

    first-person pronouns and references to personal relationships or social connections.

    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
    OGND
    -0.61
    WebVitals
    -0.59
     nahilalakip
    -0.58
    henswürdigkeiten
    -0.55
    AddTagHelper
    -0.55
     itſelf
    -0.54
    astéroïdes
    -0.54
     ligiloj
    -0.53
    AnchorStyles
    -0.52
     InputDecoration
    -0.52
    POSITIVE LOGITS
     trusts
    0.56
     whom
    0.56
     interviewed
    0.50
     trust
    0.49
    whom
    0.48
     Lam
    0.46
     consulted
    0.46
     contacted
    0.45
     Trusts
    0.45
     befri
    0.44
    Activations Density 0.174%

    No Known Activations