© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 4267
    Prev
    Next
    INDEX
    Explanations

    specific programming libraries and components used in software development

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

    Import statements, especially in code

    np_acts-logits-general · gemini-2.0-flash

    standard library includes

    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
    SharedDtor
    -0.43
     useSelector
    -0.41
    WebVitals
    -0.40
    Cubit
    -0.40
     Konzentration
    -0.39
     useRef
    -0.39
     obere
    -0.39
     Ursache
    -0.38
    ngrx
    -0.38
    currentColor
    -0.38
    POSITIVE LOGITS
    material
    0.97
    stdc
    0.84
    Material
    0.76
     AssemblyTitle
    0.75
    MATERIAL
    0.73
     Material
    0.72
     material
    0.69
     MATERIAL
    0.69
    cupertino
    0.67
     AppCompat
    0.63
    Activations Density 0.011%

    No Known Activations