© 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. 31-GEMMASCOPE-RES-131K
    11. 90615
    Prev
    Next
    INDEX
    Explanations

    terms related to technology and computing, particularly in the context of programming and system architecture

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

    governing or controlling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PRNewswire
    -0.34
    omitempty
    -0.34
    @[
    -0.32
    舺
    -0.30
    äld
    -0.29
     communiquez
    -0.29
    olstadt
    -0.29
     partire
    -0.28
    Conc
    -0.28
    Da
    -0.28
    POSITIVE LOGITS
     responsible
    1.18
     responsável
    1.04
    responsible
    0.98
     responsáveis
    0.98
     governing
    0.90
     odpowiedzial
    0.87
     controlling
    0.87
     sponsoring
    0.86
     supporting
    0.85
     overseeing
    0.84
    Activations Density 0.353%

    No Known Activations