© 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. 6538
    Prev
    Next
    INDEX
    Explanations

    abbreviations and technical terms related to programming or data

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

    Hexadecimal strings and .dll filepaths

    np_acts-logits-general · gemini-2.0-flash

    foegk specific URLs

    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
     rather
    -0.30
     successfully
    -0.28
    uchungen
    -0.28
     太郎
    -0.27
     Fø
    -0.27
    ToolTip
    -0.26
     reliably
    -0.26
     educated
    -0.26
    っこう
    -0.26
     mie
    -0.25
    POSITIVE LOGITS
     يتيمه
    0.81
    Jeografia
    0.65
     disambiguazione
    0.64
     nakalista
    0.64
     AttributeSet
    0.63
    Cyfeiriadau
    0.62
    parsedMessage
    0.62
    #+#
    0.62
     Мексичка
    0.60
    niająca
    0.57
    Activations Density 0.116%

    No Known Activations