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. 0-GEMMASCOPE-RES-16K
    6. 6922
    Prev
    Next
    INDEX
    Explanations

    instances of the beginning of new paragraphs or sections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setVerticalGroup
    -0.94
    RenderAtEndOf
    -0.88
    \{\\
    -0.85
     تضيفلها
    -0.84
    تقاوى
    -0.82
     snippetHide
    -0.80
    enumi
    -0.79
     متعلقه
    -0.79
     himo
    -0.79
     nakalista
    -0.78
    POSITIVE LOGITS
    1
    1.45
    <bos>
    1.06
    2
    0.92
    8
    0.74
    0
    0.69
    5
    0.69
    7
    0.68
    9
    0.63
    4
    0.61
    3
    0.61
    Activations Density 0.560%

    No Known Activations