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. 14304
    Prev
    Next
    INDEX
    Explanations

    actions related to the combination, merging, or formation of components in a process

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

    preceding verbs like "become", "form", or "create"

    np_acts-logits-general · gemini-2.0-flash

    form, create, become

    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
    eachtet
    -0.60
    Begriffsklä
    -0.59
     مرئيه
    -0.56
    Autowired
    -0.55
     Савезне
    -0.55
    fseek
    -0.54
    الحياه
    -0.53
    HomeController
    -0.53
     مؤرشف
    -0.53
    entance
    -0.52
    POSITIVE LOGITS
     forming
    1.92
     formando
    1.56
     Forming
    1.54
     membentuk
    1.51
    forming
    1.43
     formar
    1.41
     creating
    1.41
     create
    1.39
     creates
    1.36
     образу
    1.31
    Activations Density 0.993%

    No Known Activations