© 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-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 9705
    Prev
    Next
    INDEX
    Explanations

    phrases related to clinical research and trial details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     دیکھیے
    -0.48
    telle
    -0.43
     INTEGR
    -0.43
     Mon
    -0.42
    сками
    -0.40
    tel
    -0.40
     shui
    -0.40
     samme
    -0.40
    yce
    -0.40
    ofing
    -0.40
    POSITIVE LOGITS
    MemoryWarning
    0.83
    ValueStyle
    0.72
     demais
    0.69
     others
    0.69
     BoxFit
    0.68
    Geplaatst
    0.67
    GOTREF
    0.67
     Others
    0.65
    sidemargin
    0.65
     Otros
    0.64
    Activations Density 0.451%

    No Known Activations