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. 21-GEMMASCOPE-RES-16K
    6. 6689
    Prev
    Next
    INDEX
    Explanations

    phrases related to direction, progression, or movement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/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.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.62
     arrivo
    -0.58
    /
    -0.55
     coming
    -0.54
     acercarse
    -0.53
     Coming
    -0.50
    甫
    -0.49
     kemajuan
    -0.49
    bboxes
    -0.48
     yaklaş
    -0.47
    POSITIVE LOGITS
     виправивши
    0.84
    انيف
    0.84
    InSection
    0.70
    GEBURTSDATUM
    0.69
    :✨
    0.67
     springfox
    0.65
    enterOuterAlt
    0.64
     يتيمه
    0.63
     елның
    0.62
     دیکھیے
    0.61
    Activations Density 0.100%

    No Known Activations