© 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. 13658
    Prev
    Next
    INDEX
    Explanations

    specific commands or keywords related to data handling and processing operations

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

    Technical or scientific descriptions

    np_acts-logits-general · gemini-2.0-flash

    detection perform evaluating algorithm physical estimation

    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
    俨
    -0.32
    appName
    -0.29
     acordo
    -0.28
    pasang
    -0.28
     named
    -0.28
     hati
    -0.28
    vertre
    -0.28
    हि
    -0.28
     kalender
    -0.28
    ˈ
    -0.27
    POSITIVE LOGITS
     ſche
    0.60
    ➌
    0.59
     myſelf
    0.56
     snippetHide
    0.56
    ſelf
    0.56
    antası
    0.54
    AddTagHelper
    0.53
    writeFieldEnd
    0.53
     imagui
    0.51
     itſelf
    0.51
    Activations Density 1.069%

    No Known Activations