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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 13521
    Prev
    Next
    INDEX
    Explanations

    programming terms and structures related to data handling and updating processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    󠁴
    -0.34
     mahdol
    -0.34
     dimaksud
    -0.34
    aronder
    -0.34
     Früh
    -0.33
    说法
    -0.33
    🦵
    -0.32
     bordir
    -0.32
     sebaik
    -0.31
     compét
    -0.31
    POSITIVE LOGITS
    tagHelperRunner
    0.71
     queſta
    0.69
     Normdatei
    0.54
    JKLM
    0.54
    TAWA
    0.54
    Demografie
    0.53
     nahilalakip
    0.52
     transfieras
    0.52
    Попис
    0.50
    CppMethod
    0.49
    Activations Density 0.584%

    No Known Activations