© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 1607
    Prev
    Next
    INDEX
    Explanations

    elements related to statistical data representation and analysis in research reports

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

    figures or tables

    np_acts-logits-general · gemini-2.0-flash

    table citations and references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nestjs
    -0.45
     Kras
    -0.41
    alles
    -0.37
    cin
    -0.36
    %)$
    -0.36
    ENTY
    -0.36
    formatDate
    -0.36
     dates
    -0.36
    baz
    -0.35
    SimpleDateFormat
    -0.35
    POSITIVE LOGITS
    httphttps
    0.66
    istoitu
    0.63
    脚注の使い方
    0.60
     nakalista
    0.57
    UrlResolution
    0.54
    الحياه
    0.51
    Enllaces
    0.50
    ventud
    0.49
     graphiques
    0.49
    Hauptartikel
    0.48
    Activations Density 1.189%

    No Known Activations