© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1633
    Prev
    Next
    INDEX
    Explanations

    titles and phrases related to themes of disturbance and conflict

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

    often followed by prepositions or punctuation

    np_acts-logits-general · gemini-2.0-flash

    song and book titles

    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
     doğru
    -0.39
    又は
    -0.38
     pravi
    -0.38
    弁
    -0.37
     long
    -0.36
    gway
    -0.35
     inoxydable
    -0.35
    noOf
    -0.35
     grossen
    -0.34
     analogous
    -0.34
    POSITIVE LOGITS
     ब्रेकडाउन
    0.68
     AppCompatTheme
    0.66
    TintMode
    0.66
     betweenstory
    0.66
    ConstraintMaker
    0.63
     المعيارى
    0.62
     resourceCulture
    0.58
     disambiguazione
    0.57
     CURIAM
    0.56
    BufferException
    0.54
    Activations Density 0.214%

    No Known Activations