© 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. 4400
    Prev
    Next
    INDEX
    Explanations

    concepts and discussions that involve depth, intensity, and profound insights

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

    "deep"

    np_acts-logits-general · gemini-2.0-flash

    deep qualities and states

    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
     queſta
    -0.65
     mList
    -0.63
     getItemCount
    -0.63
    뀔
    -0.61
     ſind
    -0.60
     AssemblyCompany
    -0.59
    ésultats
    -0.57
    UserScript
    -0.56
     iconLine
    -0.56
    BufferException
    -0.56
    POSITIVE LOGITS
     deep
    1.14
     DEEP
    1.05
    Deep
    1.05
     Deep
    1.05
    deep
    1.04
     profundo
    0.96
     deeply
    0.91
     profundos
    0.91
     depth
    0.90
    Depth
    0.88
    Activations Density 0.094%

    No Known Activations