© 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. 33-GEMMASCOPE-RES-16K
    6. 907
    Prev
    Next
    INDEX
    Explanations

    terms related to repetition and repeated measures in studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iloj
    -0.38
    SourceChecksum
    -0.36
    tahankan
    -0.36
     насељу
    -0.36
    +'/
    -0.36
    getManager
    -0.35
    zielle
    -0.35
    ="./
    -0.35
     Warenkorb
    -0.35
    URLConnection
    -0.35
    POSITIVE LOGITS
     endlessly
    0.54
    +#+#
    0.54
    posedge
    0.53
     cycles
    0.53
     Repe
    0.52
     indefinitely
    0.50
    ❹
    0.48
     repeats
    0.46
    一遍
    0.46
    ɵɵelementStart
    0.46
    Activations Density 0.283%

    No Known Activations