Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15382
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and structure related to API and resource handling

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

    Code snippets or XML-like syntax

    np_acts-logits-general · gemini-2.0-flash

    Spring expression language

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    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
     Millard
    -0.36
     GlobalKey
    -0.35
     cu
    -0.35
    ตร
    -0.34
     QtCore
    -0.34
    UserScript
    -0.33
     knex
    -0.33
     PhpStorm
    -0.33
     pin
    -0.32
     seed
    -0.32
    POSITIVE LOGITS
     SPRING
    0.62
     Spring
    0.62
    Spring
    0.59
     spring
    0.57
     متعلقه
    0.57
    spring
    0.55
    aarrggbb
    0.54
     estekak
    0.53
    AndEndTag
    0.51
    spel
    0.50
    Activations Density 0.088%

    No Known Activations