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. 5680
    Prev
    Next
    INDEX
    Explanations

    names of educational institutions, particularly universities

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

    numeric and symbolic lists

    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
    続きます
    -0.43
     betweenstory
    -0.41
    \}\\
    -0.40
    sendLogPayload
    -0.40
     Ers
    -0.40
    unicip
    -0.40
    iſh
    -0.39
    RTEE
    -0.38
    RefNanny
    -0.38
     Tenggara
    -0.38
    POSITIVE LOGITS
     فريبيس
    0.52
    +#+
    0.46
     المعيارى
    0.44
    getSystemService
    0.43
     Wicidata
    0.42
     للمعارف
    0.42
     astore
    0.41
     CURIAM
    0.40
     مرئيه
    0.40
    Datuak
    0.40
    Activations Density 0.042%

    No Known Activations