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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 11621
    Prev
    Next
    INDEX
    Explanations

    repetitive phrases and connections in formal documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <eos>
    -0.58
    .
    -0.55
     or
    -0.52
    :
    -0.51
     (
    -0.49
    רה
    -0.46
    bah
    -0.46
     IPA
    -0.46
    GV
    -0.45
     /
    -0.44
    POSITIVE LOGITS
    tagext
    0.94
    PhysRevD
    0.88
    tagHelperRunner
    0.87
    DockStyle
    0.86
     незавершена
    0.86
    تقاوى
    0.85
     esternos
    0.85
    énario
    0.82
    BeginInit
    0.80
    GraphicsUnit
    0.80
    Activations Density 0.329%

    No Known Activations