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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 9757
    Prev
    Next
    INDEX
    Explanations

    technical terms and structured elements related to coding and networking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    IUrlHelper
    -0.54
     makeStyles
    -0.49
    DrawerToggle
    -0.47
     useState
    -0.45
    useState
    -0.43
     initState
    -0.43
    djangoproject
    -0.42
    IsMutable
    -0.42
     RequestMethod
    -0.41
    ToBounds
    -0.41
    POSITIVE LOGITS
    Autoritní
    0.68
    rungsseite
    0.53
     Chwiliwch
    0.52
    RTLI
    0.50
    Personendaten
    0.49
     utafitiHapana
    0.45
     digress
    0.43
    ViewFeatures
    0.42
    Derbyniad
    0.42
    Trama
    0.40
    Activations Density 0.660%

    No Known Activations