© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 4037
    Prev
    Next
    INDEX
    Explanations

    references to interdisciplinary research and methodologies in biological and computational sciences

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

    Using methods or techniques

    np_acts-logits-general · gemini-2.0-flash

    application of techniques

    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
    MLLoader
    -0.94
    IntoConstraints
    -0.88
    webElementXpaths
    -0.84
    DockStyle
    -0.81
    InSection
    -0.79
    +#+#
    -0.78
    urlpatterns
    -0.76
     '\\;'
    -0.75
     ArrayAdapter
    -0.72
     TextInputType
    -0.71
    POSITIVE LOGITS
     utilizing
    0.74
     utilising
    0.73
     memanfaatkan
    0.71
     Utilizing
    0.68
     leveraging
    0.66
    を活用
    0.65
     combining
    0.64
     utilise
    0.64
     utilizar
    0.64
     using
    0.63
    Activations Density 0.743%

    No Known Activations