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. 4865
    Prev
    Next
    INDEX
    Explanations

    elements related to artistic creation and guidance in a structured environment

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

    Code, math, or computer-related terms

    np_acts-logits-general · gemini-2.0-flash

    Russian and English place names

    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
     itſelf
    -0.85
    EndContext
    -0.80
    LEncoder
    -0.80
     дописавши
    -0.77
     habet
    -0.76
     것이다
    -0.75
    tır
    -0.74
    apunov
    -0.72
     pylint
    -0.72
    isFull
    -0.72
    POSITIVE LOGITS
    ,
    0.60
     —
    0.49
     -
    0.47
    —
    0.45
    .
    0.44
    шку
    0.43
     –
    0.43
    ReusableCell
    0.40
     Drittan
    0.40
    planet
    0.39
    Activations Density 0.043%

    No Known Activations