© 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. 14-GEMMASCOPE-RES-16K
    6. 7646
    Prev
    Next
    INDEX
    Explanations

    references to codes or identifiers, particularly in a structured data format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.67
    étoit
    -0.61
     Geiſt
    -0.59
    enumii
    -0.58
    ̚
    -0.57
    GHIJKLM
    -0.57
    󠁢
    -0.57
     dieſer
    -0.57
     queſta
    -0.57
    <?
    -0.57
    POSITIVE LOGITS
    aarrggbb
    0.35
    ApplicationTests
    0.35
    Референце
    0.32
    GEBURTSDATUM
    0.32
     red
    0.31
     tem
    0.29
     symbol
    0.28
     ύ
    0.28
    oredCriteria
    0.27
     кӀ
    0.26
    Activations Density 0.679%

    No Known Activations