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. 13428
    Prev
    Next
    INDEX
    Explanations

    numeric data and measurements related to science and research

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

    Numbers starting with "0."

    np_acts-logits-general · gemini-2.0-flash

    numbers and decimal values

    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
     ſtand
    -0.54
    SpringBootTest
    -0.48
     tänka
    -0.46
    essentiel
    -0.46
     tranſ
    -0.45
    StackNavigator
    -0.45
     ſtre
    -0.45
     TextAppearance
    -0.44
     faſt
    -0.44
     plancher
    -0.44
    POSITIVE LOGITS
    GEBURTSDATUM
    0.63
    ⏟
    0.52
     ویکی‌آمباردا
    0.52
    audiovisuel
    0.50
    PostInfinity
    0.50
    verwijspagina
    0.49
    outWeight
    0.49
    enumi
    0.47
    __":
    
    0.46
    qtype
    0.46
    Activations Density 0.955%

    No Known Activations