© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 38454
    Prev
    Next
    INDEX
    Explanations

    formatted numeric values and their representation in programming language syntax

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

    numbers and formatting specifiers

    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
    bibfield
    -0.70
     CreateTagHelper
    -0.70
    linawan
    -0.62
    ]")]
    -0.61
    iſchen
    -0.60
    存于互联网档案馆
    -0.59
     Geſch
    -0.58
    amssymb
    -0.57
     مشين
    -0.57
    mobileqq
    -0.56
    POSITIVE LOGITS
     &___
    0.34
    URLException
    0.32
     shop
    0.29
     gọn
    0.28
    fromLTRB
    0.28
     الص
    0.28
     thập
    0.28
    shop
    0.27
     Supp
    0.27
     skj
    0.27
    Activations Density 0.011%

    No Known Activations