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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 9751
    Prev
    Next
    INDEX
    Explanations

    HTML elements and attributes related to navigation and interactive components

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

    HTML related to buttons and toggles

    np_acts-logits-general · gemini-2.0-flash

    HTML role attribute

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    IActionResult
    -0.44
    HttpGet
    -0.26
     nød
    -0.25
    initComponents
    -0.22
     About
    -0.22
    About
    -0.21
     ویکی‌پدیا
    -0.21
     nemlig
    -0.21
     iesp
    -0.20
    ModelForm
    -0.20
    POSITIVE LOGITS
     للمعارف
    0.84
    IVEREF
    0.82
     AssemblyCompany
    0.82
    Vidite
    0.80
    󠀠
    0.74
     nahilalakip
    0.73
    featureID
    0.72
    [@BOS@]
    0.71
    WriteTagHelper
    0.71
    <unused17>
    0.70
    Activations Density 0.207%

    No Known Activations