© 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. 13059
    Prev
    Next
    INDEX
    Explanations

    numerical data related to statistics and percentages

    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
     MonoBehaviour
    -0.35
     légale
    -0.34
     chinoise
    -0.33
     humaine
    -0.32
     fijo
    -0.32
    Linki
    -0.32
     Denken
    -0.32
    loroethene
    -0.32
     vectorielle
    -0.31
    ếc
    -0.30
    POSITIVE LOGITS
    хьтан
    0.68
     يتيمه
    0.66
     typelib
    0.65
     newOwner
    0.60
    openzeppelin
    0.57
    parsedMessage
    0.54
    UserScript
    0.54
    tagHelperRunner
    0.52
    AddAttribute
    0.52
    MessageTagHelper
    0.52
    Activations Density 0.289%

    No Known Activations