© 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. 10-GEMMASCOPE-RES-16K
    6. 7222
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a range or spectrum of options or variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fign
    -0.36
     CSD
    -0.36
     receiver
    -0.35
     Receiver
    -0.35
     transf
    -0.35
    UIControlState
    -0.35
    tagHelperRunner
    -0.34
    msgTypes
    -0.33
    !*\
    -0.33
     git
    -0.32
    POSITIVE LOGITS
     utafitiHapana
    0.65
     nahilalakip
    0.60
    antaranya
    0.59
    :✨
    0.53
     ranging
    0.51
    jména
    0.50
     From
    0.49
    ranging
    0.48
     Desde
    0.48
     Whether
    0.48
    Activations Density 0.197%

    No Known Activations