© 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. 38895
    Prev
    Next
    INDEX
    Explanations

    parts of the text related to data files and their attributes

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

    code-like delimiters

    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
    rungsseite
    -1.02
     disambiguazione
    -0.92
    ſcher
    -0.85
    AndEndTag
    -0.84
    addCriterion
    -0.84
    IsMutable
    -0.82
    iſen
    -0.82
    IUrlHelper
    -0.77
    UserScript
    -0.76
     $_(
    -0.75
    POSITIVE LOGITS
    ↵↵↵↵
    0.45
    ↵↵↵
    0.44
    ↵↵↵↵↵
    0.40
    Notice
    0.36
    Page
    0.36
     steder
    0.36
     kurzen
    0.35
    ↵↵
    0.35
     Notice
    0.34
    idać
    0.34
    Activations Density 0.003%

    No Known Activations