© 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. 20-GEMMASCOPE-RES-131K
    6. 16980
    Prev
    Next
    INDEX
    Explanations

    methods related to setting parameters and attributes in programming

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

    set `property` value

    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
     Мексичка
    -0.70
    modelBuilder
    -0.61
     ویکی‌پدی
    -0.60
    unhofer
    -0.59
    TagMode
    -0.58
    новниш
    -0.58
     Roskov
    -0.57
    Сылтамалар
    -0.55
    RegressionTest
    -0.54
     zwiſchen
    -0.54
    POSITIVE LOGITS
     setId
    0.88
     setEmail
    0.69
     AssemblyCompany
    0.52
     setLoading
    0.48
     setUsername
    0.46
    GOTREF
    0.46
     setUser
    0.46
     setName
    0.45
     setTotal
    0.45
     setPassword
    0.43
    Activations Density 0.000%

    No Known Activations