© 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. 7786
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to scientific methods and legal matters

    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
     desk
    -0.42
    setupUi
    -0.40
     об
    -0.39
    onViewCreated
    -0.37
     rest
    -0.36
     Brun
    -0.35
     hinter
    -0.35
     burn
    -0.34
     half
    -0.33
     uneasy
    -0.32
    POSITIVE LOGITS
    enderror
    0.67
     '\\;'
    0.61
    twimg
    0.58
    XmlAccessType
    0.56
     ffilm
    0.56
     BoxFit
    0.56
     MainAxisSize
    0.56
    jména
    0.54
    GEBURTS
    0.53
     gynhyrchwyd
    0.51
    Activations Density 2.286%

    No Known Activations