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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 16227
    Prev
    Next
    INDEX
    Explanations

    phrases related to processes and transitions over time

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

    Followed by "in" or "by"

    np_acts-logits-general · gemini-2.0-flash

    states or results

    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
    DllImport
    -0.46
     stuff
    -0.40
     Tamil
    -0.38
     GoogleFonts
    -0.37
     ostavi
    -0.36
     Spisak
    -0.35
     recipe
    -0.35
    瞰
    -0.34
    chloric
    -0.34
     Pref
    -0.34
    POSITIVE LOGITS
     during
    0.58
    AndEndTag
    0.54
    CrossRef
    0.52
    OGND
    0.52
    hyrchwyd
    0.51
    umumkan
    0.49
    原始内容存档于
    0.48
    rungsseite
    0.47
     مؤرشف
    0.47
    basicConfig
    0.46
    Activations Density 0.499%

    No Known Activations