© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 6-GEMMASCOPE-RES-16K
    11. 1987
    Prev
    Next
    INDEX
    Explanations

    opening and closing braces, brackets, and parentheses, indicating structure in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Vere
    -0.53
    cendental
    -0.52
    pausal
    -0.49
    mitian
    -0.49
     capelli
    -0.49
     Tele
    -0.48
     remaja
    -0.47
    ayakan
    -0.45
    zeciw
    -0.44
     taboo
    -0.43
    POSITIVE LOGITS
    ={({
    0.96
    tagHelperRunner
    0.89
    :+:
    0.87
    ⓧ
    0.85
    (({
    0.85
     kasarigan
    0.83
    __(/*!
    0.80
    UnknownFieldSet
    0.76
     Efq
    0.74
     &___
    0.72
    Activations Density 0.023%

    No Known Activations