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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11-GEMMASCOPE-RES-16K
    6. 2022
    Prev
    Next
    INDEX
    Explanations

    references to requests and responses in web programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SpringBootTest
    -0.53
     "
    -0.52
     “
    -0.51
    阳台
    -0.49
    SizeF
    -0.49
    <eos>
    -0.47
    RunWith
    -0.47
    ("$.
    -0.47
     [
    -0.47
    +
    -0.47
    POSITIVE LOGITS
     AssemblyTitle
    0.83
    BagConstraints
    0.81
    XtraEditors
    0.77
    ^(@)
    0.77
     useRouter
    0.77
    orianCalendar
    0.74
     كومونز
    0.73
    HttpFoundation
    0.73
     ActivatedRoute
    0.70
    gonic
    0.70
    Activations Density 0.054%

    No Known Activations