© 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. 698
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and references to ownership

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

    possessive pronouns and determiners referring to people or their attributes.

    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
     itſelf
    -0.83
     myſelf
    -0.81
     himſelf
    -0.60
    IBOutlet
    -0.58
     tranſ
    -0.57
     Reſ
    -0.57
     ſal
    -0.55
     fubject
    -0.54
     purpoſe
    -0.53
     leſs
    -0.52
    POSITIVE LOGITS
     presence
    0.62
     Wikimedijinoj
    0.59
     name
    0.55
     kanssa
    0.51
     nahilalakip
    0.48
    Хьажоргаш
    0.47
    Спољашње
    0.46
     approval
    0.46
     footsteps
    0.46
     absence
    0.45
    Activations Density 0.448%

    No Known Activations