Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 15-GEMMASCOPE-RES-16K
    6. 1626
    Prev
    Next
    INDEX
    Explanations

    keywords related to niche markets and specific product offerings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Chwiliwch
    -0.59
    +#+#
    -0.54
     insistence
    -0.54
     ويكيپيديا
    -0.52
    ModelSerializer
    -0.52
    PutMapping
    -0.51
    __).
    -0.51
    DoubleQuotes
    -0.50
    wahlen
    -0.49
     دریافت‌شده
    -0.49
    POSITIVE LOGITS
     الدولى
    0.65
     forKey
    0.64
    MENAFN
    0.62
    raseña
    0.58
    ագրություններ
    0.53
     بيها
    0.51
    intégr
    0.51
    forChild
    0.50
    istoitu
    0.49
    Personendaten
    0.49
    Activations Density 0.711%

    No Known Activations