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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 64759
    Prev
    Next
    INDEX
    Explanations

    references to labels or tags and their placement information

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

    signs and labels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.49
    帖最后由
    -0.48
    SpringBootTest
    -0.38
    IActionResult
    -0.38
     setuptools
    -0.38
    UrlResolution
    -0.36
    PRWEB
    -0.36
     soma
    -0.36
    PyTuple
    -0.34
    isSuccessful
    -0.32
    POSITIVE LOGITS
     nahilalakip
    0.49
    Derbyniad
    0.47
    WebElementEntity
    0.47
    printed
    0.45
     printed
    0.45
    ftone
    0.45
     desvan
    0.44
    atellite
    0.44
    webElementXpaths
    0.43
    Бахар
    0.43
    Activations Density 0.048%

    No Known Activations