© 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. 14316
    Prev
    Next
    INDEX
    Explanations

    references to information technology and related fields

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

    Computer-related terms

    np_acts-logits-general · gemini-2.0-flash

    computer science, IT, developers

    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
    JsonKey
    -0.39
     Pons
    -0.36
     POV
    -0.35
     Frankel
    -0.33
     honed
    -0.32
    orcid
    -0.32
    owaną
    -0.32
     Jacobsen
    -0.32
     circular
    -0.32
     poster
    -0.32
    POSITIVE LOGITS
     informática
    0.76
     informatique
    0.74
    computer
    0.74
     computer
    0.74
     Computer
    0.73
     Computers
    0.73
    Computer
    0.71
     Cybersecurity
    0.70
     computers
    0.69
     COMPUTER
    0.69
    Activations Density 0.528%

    No Known Activations