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. 675
    Prev
    Next
    INDEX
    Explanations

    the start of a new section in a document

    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
     pleaſure
    -0.71
     ſeveral
    -0.70
     Monfieur
    -0.70
     themſelves
    -0.68
     myſelf
    -0.67
     незавершена
    -0.65
     doubtnut
    -0.64
    GraphicsUnit
    -0.64
     ſtate
    -0.64
     himſelf
    -0.63
    POSITIVE LOGITS
    Naissance
    0.54
     مرئيه
    0.49
    <eos>
    0.44
    blox
    0.44
    Билгалдахарш
    0.44
    צ
    0.44
     onStop
    0.44
    NavController
    0.43
    länd
    0.41
    centr
    0.41
    Activations Density 0.049%

    No Known Activations