© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 13205
    Prev
    Next
    INDEX
    Explanations

    names associated with military honors and individuals involved in those stories

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

    instances of the name "Giunta" (appearing as fragmented tokens).

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou

    the name "Giunta" and similar Italian-origin names (particularly those starting with "Gi").

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    capitalized proper names starting with “Gi” (often Italian-sounding surnames) and their component tokens within multi-part names.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    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
     OMITBAD
    -0.50
     resourceCulture
    -0.48
    MeasureSpec
    -0.38
    ActionEvent
    -0.38
    RTCF
    -0.37
    lgari
    -0.37
     Catalana
    -0.36
    EUROPA
    -0.35
    findpost
    -0.35
    Author
    -0.34
    POSITIVE LOGITS
     Gi
    0.62
     Gir
    0.60
     Gib
    0.58
     lenker
    0.54
     ги
    0.54
     gi
    0.52
    Gir
    0.52
     Gibson
    0.52
     Gig
    0.51
    Ги
    0.51
    Activations Density 0.147%

    No Known Activations