© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 1631
    Prev
    Next
    INDEX
    Explanations

    legislative terms and mandates related to regulations and laws

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

    Mandatory or required actions/rules/laws

    np_acts-logits-general · gemini-2.0-flash

    mandatory or conditional requirements

    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
     الحره
    -0.74
     AssemblyCompany
    -0.72
    endphp
    -0.70
    ukkig
    -0.63
     EconPapers
    -0.62
     كومونز
    -0.56
    RenderAtEndOf
    -0.56
     protoimpl
    -0.54
     referenties
    -0.53
     нала
    -0.53
    POSITIVE LOGITS
     künftig
    0.78
     henceforth
    0.72
     visse
    0.70
     mandatory
    0.67
     certain
    0.66
     bepaalde
    0.65
     compulsory
    0.64
    除非
    0.63
     wajib
    0.60
     unless
    0.60
    Activations Density 0.561%

    No Known Activations