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. 20-GEMMASCOPE-RES-16K
    6. 1507
    Prev
    Next
    INDEX
    Explanations

    references to specific points or statements in the text

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

    "This" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    introducing a fact or consequence

    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
     ModelExpression
    -0.79
    DockStyle
    -0.75
     виправивши
    -0.70
     thingy
    -0.68
    SOUNDBITE
    -0.67
     propOrder
    -0.67
     guys
    -0.66
     excru
    -0.65
    guys
    -0.63
     assholes
    -0.62
    POSITIVE LOGITS
     fact
    1.14
    fact
    0.84
     fato
    0.64
     lack
    0.64
    ことは
    0.63
     fapt
    0.62
     is
    0.59
     Tatsache
    0.59
     Fact
    0.58
     apparent
    0.58
    Activations Density 0.360%

    No Known Activations