© 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. 3063
    Prev
    Next
    INDEX
    Explanations

    coding functions and structures related to data manipulation and API responses

    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
    AutoScaleMode
    -0.64
     فريبيس
    -0.61
     autorytatywna
    -0.58
     Audiodateien
    -0.56
     <>",
    -0.56
     propOrder
    -0.55
    windowFixed
    -0.55
     Chwiliwch
    -0.54
    ArrowToggle
    -0.54
    ruik
    -0.53
    POSITIVE LOGITS
    Performed
    0.33
    薙
    0.32
    Impl
    0.32
     performed
    0.32
    Logging
    0.31
    Absch
    0.31
     conformance
    0.30
    ∩
    0.30
    Mid
    0.30
    sendStatus
    0.30
    Activations Density 0.363%

    No Known Activations