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. 16-GEMMASCOPE-RES-16K
    6. 6003
    Prev
    Next
    INDEX
    Explanations

    mathematical and unit conversion questions

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

    Fractions within "what is...?" questions

    np_acts-logits-general · gemini-2.0-flash

    What is a fraction of a unit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bkz
    -0.47
     kuliah
    -0.46
     regionally
    -0.45
    mkdirs
    -0.45
     الحره
    -0.44
    эффици
    -0.44
     defining
    -0.43
     mahasiswa
    -0.42
    appartamento
    -0.42
    kuli
    -0.42
    POSITIVE LOGITS
    migrationBuilder
    0.84
    bewerken
    0.79
     TestBed
    0.67
    ISupport
    0.67
    Спољашње
    0.66
     NgModule
    0.60
    قایناقلار
    0.59
    Abitanti
    0.58
    MessageTagHelper
    0.57
     Francine
    0.56
    Activations Density 1.562%

    No Known Activations