© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 99801
    Prev
    Next
    INDEX
    Explanations

    mentions of authorship or attribution in a document

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

    user names and identifiers

    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
     désolés
    -0.45
     CreateTagHelper
    -0.37
     detta
    -0.35
    QMetaType
    -0.34
    lighet
    -0.34
     alcanzó
    -0.33
     урна
    -0.33
    hilangan
    -0.33
    发表于
    -0.32
     büyü
    -0.32
    POSITIVE LOGITS
    OGND
    0.79
    帖最后由
    0.72
     kasarigan
    0.61
     المعيارى
    0.59
    Бахар
    0.57
    GIVEREF
    0.55
    verifyException
    0.54
    DebuggerNonUser
    0.54
    fjspx
    0.54
     مرئيه
    0.51
    Activations Density 0.005%

    No Known Activations