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. 13-GEMMASCOPE-RES-16K
    6. 13517
    Prev
    Next
    INDEX
    Explanations

    syntactical structures and formatting in mathematical or technical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     X
    -0.60
     Te
    -0.57
     M
    -0.57
    s
    -0.57
    之
    -0.53
     Man
    -0.53
     đ
    -0.53
    x
    -0.52
    \
    -0.52
     S
    -0.52
    POSITIVE LOGITS
     purpoſe
    1.19
     myſelf
    1.16
     raiſ
    1.15
    ſelves
    1.14
     whoſe
    1.12
     pleaſure
    1.11
     ſtill
    1.10
    ſelf
    1.10
     themſelves
    1.09
     juſt
    1.07
    Activations Density 0.774%

    No Known Activations