© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 6035
    Prev
    Next
    INDEX
    Explanations

    elements related to personal identity and cultural context

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

    words and phrases in non-English languages, particularly in contexts involving foreign text, multilingual content, or non-ASCII characters.

    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
    يكب
    -0.41
     mergeFrom
    -0.40
    contentLoaded
    -0.39
     tenu
    -0.39
     حالی
    -0.38
    rungsseite
    -0.38
    featureID
    -0.38
    AddHtmlAttribute
    -0.38
    IActionResult
    -0.37
    exercises
    -0.36
    POSITIVE LOGITS
     yours
    0.76
     theirs
    0.73
     its
    0.72
    nya
    0.72
     hers
    0.71
     him
    0.68
     său
    0.66
     ours
    0.64
     mình
    0.63
     them
    0.62
    Activations Density 0.038%

    No Known Activations