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. 21-GEMMASCOPE-RES-16K
    6. 687
    Prev
    Next
    INDEX
    Explanations

    code-related content focusing on Android programming and import statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thol
    -0.46
    ύ
    -0.45
    ἶ
    -0.44
     Empieza
    -0.43
     thư
    -0.42
    ธ์
    -0.42
     accordingly
    -0.41
     colspan
    -0.39
    Nos
    -0.38
    Ў
    -0.38
    POSITIVE LOGITS
     المعيارى
    0.90
    تقاوى
    0.83
    InitVars
    0.80
    évaluateur
    0.75
     AssemblyTitle
    0.72
    ValueStyle
    0.72
     الرياضيه
    0.72
    TagMode
    0.70
    AutoScaleMode
    0.70
    ImageContext
    0.69
    Activations Density 0.065%

    No Known Activations