© 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. 6755
    Prev
    Next
    INDEX
    Explanations

    technical terms and jargon related to specifications and adjustments in systems or processes

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

    before specific technical or uncommon terms

    np_acts-logits-general · gemini-2.0-flash

    technical terms and identifiers

    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
     anzu
    -0.32
     Shi
    -0.32
    tagHelper
    -0.31
    DECREF
    -0.31
     Famous
    -0.30
    ↵
    -0.28
     May
    -0.28
    awtextra
    -0.28
    း
    -0.28
     No
    -0.28
    POSITIVE LOGITS
     nakalista
    0.69
    ViewImports
    0.65
    Tembelea
    0.62
     PeEnEo
    0.59
     Numerade
    0.58
    SharedDtor
    0.57
    MLLoader
    0.56
    جغرافيا
    0.56
     Infórmanos
    0.55
     autorytatywna
    0.55
    Activations Density 2.210%

    No Known Activations