© 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. 13729
    Prev
    Next
    INDEX
    Explanations

    format and structure elements in code or markup languages

    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
    MemoryWarning
    -0.63
     }{@
    -0.60
    Hochspringen
    -0.59
     betweenstory
    -0.58
    UseVisualStyle
    -0.58
    enumii
    -0.57
     typelib
    -0.55
    KommentareTeilen
    -0.54
     MonoBehaviour
    -0.53
     вікісторінку
    -0.53
    POSITIVE LOGITS
     PeEnEo
    0.38
    demografi
    0.36
     дъ
    0.33
    škoda
    0.32
    אים
    0.31
    Predecesor
    0.31
    toarele
    0.31
     also
    0.30
     avances
    0.30
    TagMode
    0.30
    Activations Density 0.783%

    No Known Activations