© 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. 2992
    Prev
    Next
    INDEX
    Explanations

    entities and significant terms, including names and labels in legal and technical contexts

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

    Appearing at the start of proper nouns

    np_acts-logits-general · gemini-2.0-flash

    filing petitions or legal cases

    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
    protoimpl
    -0.71
    complexContent
    -0.70
    Vezi
    -0.56
    NewUrlParser
    -0.55
     AssemblyTitle
    -0.54
    Demografía
    -0.53
     Olímpicos
    -0.53
    fjspx
    -0.52
    ->___
    -0.51
     ***!
    -0.51
    POSITIVE LOGITS
     disambiguazione
    0.98
     समीक्षाओं
    0.84
    withstanding
    0.67
     Mep
    0.67
     Waray
    0.66
    ंदीखरीदारी
    0.64
    SupportActionBar
    0.64
    queous
    0.63
     ujednoznacz
    0.61
    NOPQRST
    0.61
    Activations Density 0.343%

    No Known Activations