Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14450
    Prev
    Next
    INDEX
    Explanations

    technical specifications and features related to audio equipment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.53
     riuscito
    -0.52
    Tires
    -0.52
    HandleFunc
    -0.51
     debole
    -0.49
     viewer
    -0.49
     UIFont
    -0.49
    bbene
    -0.48
    culature
    -0.48
     eorum
    -0.47
    POSITIVE LOGITS
     ddelweddau
    0.68
     preamp
    0.65
    writeField
    0.64
     recording
    0.60
     Recording
    0.59
     pedal
    0.58
    recording
    0.58
    PostInfinity
    0.58
     reverb
    0.57
     DSP
    0.57
    Activations Density 0.183%

    No Known Activations