© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 12484
    Prev
    Next
    INDEX
    Explanations

    instances of the word "private" and related terms

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

    private sector or practice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     ExecuteAsync
    -0.52
    __).
    -0.50
    AddTagHelper
    -0.46
    hadapi
    -0.46
    AccessorTable
    -0.46
     whereof
    -0.46
    ătoare
    -0.45
    siune
    -0.45
     consigo
    -0.44
     Happened
    -0.43
    POSITIVE LOGITS
    Private
    0.70
     Private
    0.67
    private
    0.55
     sector
    0.55
     PRIVATE
    0.51
    PRIVATE
    0.51
     private
    0.51
     priv
    0.47
     privat
    0.47
     sphere
    0.45
    Activations Density 0.018%

    No Known Activations