Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 3595
    Prev
    Next
    INDEX
    Explanations

    time stamps and date formats

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

    Dates with day '0' or '1' after the month

    np_acts-logits-general · gemini-2.0-flash

    foreign characters and 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
    fjspx
    -0.39
    لينكات
    -0.35
    ContentAsync
    -0.35
    HXLINE
    -0.34
    “…
    -0.34
    <!--[
    -0.34
     wherever
    -0.33
     nawet
    -0.33
    GEBURTSDATUM
    -0.33
     “…
    -0.32
    POSITIVE LOGITS
    iſchen
    0.59
     femininas
    0.59
     queſto
    0.59
    ᅝ
    0.59
    iſche
    0.57
    Bibitem
    0.56
    ágenes
    0.56
    ๣
    0.56
     Kali
    0.56
    iſen
    0.55
    Activations Density 0.093%

    No Known Activations