© 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. 22-GEMMASCOPE-RES-16K
    6. 6678
    Prev
    Next
    INDEX
    Explanations

    mathematical relationships and calculations involving differences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LookAnd
    -0.46
     équi
    -0.39
     poveznice
    -0.38
    ariat
    -0.37
     agreement
    -0.36
    mainen
    -0.36
    Hinweise
    -0.35
     curls
    -0.35
    ambilan
    -0.35
     heureux
    -0.35
    POSITIVE LOGITS
    addPreferredGap
    0.61
    RectangleBorder
    0.52
     Paglinawan
    0.48
    <?
    0.48
    المناصب
    0.47
    antiation
    0.46
     unknownFields
    0.46
    archiviato
    0.45
     subtract
    0.44
    MockMvc
    0.43
    Activations Density 0.542%

    No Known Activations