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. 2419
    Prev
    Next
    INDEX
    Explanations

    elements related to user interface components and their configurations

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

    dirs","rearrange","week","NF"

    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
    хьтан
    -0.59
     linkovi
    -0.52
    Jereo
    -0.49
    ChildScrollView
    -0.47
    expandindo
    -0.46
    Ӕ
    -0.46
    Демографія
    -0.46
    BufferException
    -0.45
     ivelany
    -0.45
    adaptiveStyles
    -0.41
    POSITIVE LOGITS
    webElementGuid
    0.39
     épaules
    0.38
     hochzeit
    0.38
     Output
    0.36
     Appointment
    0.36
    Specifiche
    0.36
     فريبيس
    0.36
    Inflater
    0.35
    ountain
    0.35
    Див
    0.35
    Activations Density 0.002%

    No Known Activations