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. 20-GEMMASCOPE-RES-16K
    6. 3185
    Prev
    Next
    INDEX
    Explanations

    terms related to software updates and versioning

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

    Followed by auxiliary verbs in Chinese

    np_acts-logits-general · gemini-2.0-flash

    is coming soon; already happened; or whether

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UnusedPrivate
    -0.75
    จึง
    -0.67
     meanwhile
    -0.66
    الإنجليزية
    -0.63
    dann
    -0.63
    ก็
    -0.60
     AttributeSet
    -0.59
     này
    -0.58
     getItemId
    -0.57
     meantime
    -0.57
    POSITIVE LOGITS
    EditorBrowsable
    0.69
    ResumeLayout
    0.63
    stateMutability
    0.56
     like
    0.51
     be
    0.50
     مانند
    0.48
     need
    0.48
     existed
    0.48
    TagMode
    0.47
    deleteById
    0.46
    Activations Density 0.034%

    No Known Activations