© 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-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 4421
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references related to court cases and judgments

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

    Punctuation after certain words

    np_acts-logits-general · gemini-2.0-flash

    pro se petitioners authors

    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
     bağlantılar
    -0.53
    bewerken
    -0.52
     affari
    -0.45
    AndEndTag
    -0.44
     invokingState
    -0.42
    dafx
    -0.42
     saites
    -0.41
    GEBURTSDATUM
    -0.40
    以上就是
    -0.40
    antlr
    -0.38
    POSITIVE LOGITS
     Cuth
    0.46
    GOTREF
    0.42
    BeginInit
    0.41
    StoryboardSegue
    0.40
     deren
    0.40
    الدراسه
    0.40
     neighbouring
    0.40
    agg
    0.40
     Bucure
    0.39
     bestä
    0.39
    Activations Density 0.964%

    No Known Activations