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. 450
    Prev
    Next
    INDEX
    Explanations

    word combinations that indicate interconnections or relationships

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

    conjunctions and their frequency within sentences

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

    the word "and," especially when used as a conjunction to connect phrases or elements.

    oai_token-act-pair · gpt-4oTriggered by @timna
    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
    esterday
    -0.78
     FontFamily
    -0.71
    ardless
    -0.70
    المناصب
    -0.69
    berdayakan
    -0.68
     BoxFit
    -0.67
    ignty
    -0.66
     useAppContext
    -0.66
    polation
    -0.66
    ernalia
    -0.65
    POSITIVE LOGITS
    os
    0.55
    ⓧ
    0.54
    ot
    0.54
    ap
    0.53
    ut
    0.52
    ur
    0.50
    it
    0.50
    jan
    0.50
    ol
    0.49
     own
    0.49
    Activations Density 0.214%

    No Known Activations