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. 14-GEMMASCOPE-RES-16K
    6. 12920
    Prev
    Next
    INDEX
    Explanations

    references to figures, diagrams, or illustrative content within a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ंदीखरीदारी
    -0.68
    حياتها
    -0.61
    inerja
    -0.60
    +#+
    -0.58
     disponibilités
    -0.57
    amaño
    -0.56
    IContainer
    -0.56
    Și
    -0.55
     setType
    -0.54
    oient
    -0.53
    POSITIVE LOGITS
    CppCodeGen
    0.72
    dropIfExists
    0.65
    see
    0.64
    setVerticalGroup
    0.63
    rawDesc
    0.61
    AndEndTag
    0.58
    RectangleBorder
    0.57
    μβρίου
    0.56
     שוליים
    0.56
    thus
    0.55
    Activations Density 0.739%

    No Known Activations