© 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. 519
    Prev
    Next
    INDEX
    Explanations

    elements related to programming concepts and functions

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

    Code related to vertices or points

    np_acts-logits-general · gemini-2.0-flash

    geometric shapes and lines

    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
    tagHelperRunner
    -0.55
    DockStyle
    -0.47
    principalColumn
    -0.43
    addPreferredGap
    -0.43
     nawr
    -0.41
     susp
    -0.41
     وتسجيلات
    -0.41
    帖最后由
    -0.40
     disambiguazione
    -0.40
     jScrollPane
    -0.40
    POSITIVE LOGITS
     points
    0.48
    vertex
    0.45
    Points
    0.44
     точка
    0.44
     point
    0.43
    Населення
    0.42
     POINTS
    0.42
    Grath
    0.42
    nitts
    0.42
     gate
    0.41
    Activations Density 0.470%

    No Known Activations