© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 1618
    Prev
    Next
    INDEX
    Explanations

    terms related to elevated medical conditions, particularly those involving hyper- prefixes and associated biochemical markers

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

    starting with "hyper"

    np_acts-logits-general · gemini-2.0-flash

    hyper-

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BeginContext
    -0.90
    antaranya
    -0.88
     propOrder
    -0.85
     Gans
    -0.82
     CWE
    -0.78
    adaptiveStyles
    -0.76
     onCreateView
    -0.74
    findpost
    -0.74
    Sucesor
    -0.73
     getItemCount
    -0.72
    POSITIVE LOGITS
    <h6>
    0.64
     plead
    0.61
     läs
    0.60
     Hyper
    0.58
    <h5>
    0.58
    cfm
    0.56
    PAIGN
    0.55
     гипер
    0.54
    meth
    0.54
     Hiper
    0.52
    Activations Density 0.306%

    No Known Activations