© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 14349
    Prev
    Next
    INDEX
    Explanations

    terms related to "mer" as a prefix or suffix in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    */].
    -0.50
    setAccessible
    -0.49
     **/
    -0.49
    ſelves
    -0.48
     Majefty
    -0.46
     ſaid
    -0.45
    AccessFile
    -0.44
    saco
    -0.43
    batore
    -0.41
     kæ
    -0.41
    POSITIVE LOGITS
     Mer
    2.56
     mer
    2.52
    Mer
    2.48
     MER
    2.30
    mer
    2.17
    MER
    2.02
     Merc
    1.70
     merc
    1.65
     Merit
    1.63
     Мер
    1.63
    Activations Density 0.186%

    No Known Activations