© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 17015
    Prev
    Next
    INDEX
    Explanations

    phrases related to social and digital interactions

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

    study, analyses, media, traditions

    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
     AssemblyTitle
    -0.62
    紆
    -0.48
     Entscheid
    -0.42
     pemikiran
    -0.41
     piş
    -0.40
     myś
    -0.40
     sını
    -0.40
     المعيارى
    -0.40
     inférieure
    -0.40
     myśli
    -0.40
    POSITIVE LOGITS
    ExecuteReader
    0.45
     SAH
    0.43
     Bearer
    0.43
    ahme
    0.43
     squash
    0.42
     bearer
    0.42
     osmosis
    0.42
     BAC
    0.42
    bearers
    0.40
     homo
    0.39
    Activations Density 0.191%

    No Known Activations