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. 4601
    Prev
    Next
    INDEX
    Explanations

    references to database management and configuration issues

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

    German words or phrases

    np_acts-logits-general · gemini-2.0-flash

    German modal verbs, sentences

    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
    tificates
    -0.67
    ICOLON
    -0.65
    isFull
    -0.64
    schuhe
    -0.63
    enada
    -0.63
    resaid
    -0.62
    apunov
    -0.62
    HomeAsUpEnabled
    -0.61
    ționale
    -0.60
    othesis
    -0.60
    POSITIVE LOGITS
    soort
    0.55
    EnumMember
    0.49
    MemoryWarning
    0.49
    tvguidetime
    0.46
    SizeMode
    0.46
     importância
    0.44
    RenderAtEndOf
    0.44
    tagHelperRunner
    0.43
    بوابة
    0.43
     CSL
    0.40
    Activations Density 0.078%

    No Known Activations