© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 20669
    Prev
    Next
    INDEX
    Explanations

    terms related to organizations, programs, and documents within various contexts

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

    cases, organizations, projects, programs

    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
     which
    -0.62
    enderror
    -0.47
     quien
    -0.45
     которые
    -0.45
    which
    -0.41
    GEBURTSDATUM
    -0.41
    AnchorTagHelper
    -0.41
     который
    -0.40
     whom
    -0.40
     who
    -0.38
    POSITIVE LOGITS
     dubbed
    0.60
     nicknamed
    0.60
     described
    0.59
     touted
    0.54
     punctuated
    0.54
     likened
    0.53
     featuring
    0.53
     reminiscent
    0.52
     rife
    0.52
     hailed
    0.52
    Activations Density 0.151%

    No Known Activations