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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 25-GEMMASCOPE-RES-16K
    6. 3473
    Prev
    Next
    INDEX
    Explanations

    numerical or arithmetic data structures and their elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⓧ
    -0.54
     betweenstory
    -0.36
     nahilalakip
    -0.35
    ViewImports
    -0.33
    новништво
    -0.30
    SpringBootTest
    -0.28
    RenderAtEndOf
    -0.27
    AndEndTag
    -0.27
    SourceChecksum
    -0.27
    клопе
    -0.27
    POSITIVE LOGITS
    <bos>
    0.55
    ρυ
    0.19
     allAfrica
    0.18
     semelh
    0.16
     VIDEOTAPE
    0.16
    λοι
    0.16
     ansik
    0.15
     estadounid
    0.15
     queſta
    0.15
     vägen
    0.14
    Activations Density 19.551%

    No Known Activations