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. 4582
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and structuring elements used in programming or mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Set" (data structure or mathematical concept)

    np_acts-logits-general · gemini-2.0-flash

    set operations or elements

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    rician
    -0.51
    ="#"><
    -0.49
    <?,
    -0.49
    crollView
    -0.48
     <>",
    -0.48
    στημα
    -0.46
    directional
    -0.46
    spheric
    -0.46
    istat
    -0.45
    öße
    -0.44
    POSITIVE LOGITS
     HashSet
    1.08
     Set
    1.08
    Set
    1.03
    HashSet
    1.00
     set
    1.00
     Sets
    0.95
    set
    0.95
     sets
    0.93
     SETS
    0.88
    SET
    0.88
    Activations Density 0.802%

    No Known Activations