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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 3-GEMMASCOPE-RES-16K
    6. 6129
    Prev
    Next
    INDEX
    Explanations

    brackets and nested structures in mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -1.17
     pleaſure
    -1.13
     myſelf
    -1.11
    ſelves
    -1.05
     Jefus
    -1.05
     preſent
    -1.05
     Reſ
    -1.05
     raiſ
    -1.05
     Majefty
    -1.05
     ſtate
    -1.03
    POSITIVE LOGITS
    {
    1.08
     ‘
    0.83
     “
    0.82
    “
    0.72
    (
    0.72
    /
    0.62
    __["
    0.61
    []{
    0.61
    [toxicity=0]
    0.60
    ‘
    0.60
    Activations Density 0.121%

    No Known Activations