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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4143
    Prev
    Next
    INDEX
    Explanations

    terms and phrases indicating quantity or references to groups

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

    "Some" followed by nouns/facts/reasons/ways

    np_acts-logits-general · gemini-2.0-flash

    some specific instances

    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
     للاسماء
    -0.86
     للمعارف
    -0.76
     Réponses
    -0.76
    ReusableCell
    -0.73
     gynhyrchwyd
    -0.69
     CreateTagHelper
    -0.67
     ModelExpression
    -0.66
     مشين
    -0.65
    :]:
    -0.63
    InjectAttribute
    -0.62
    POSITIVE LOGITS
     parts
    0.80
     aspects
    0.72
     people
    0.71
     areas
    0.66
     regions
    0.64
     jurisdictions
    0.61
     kinds
    0.58
     types
    0.58
     instances
    0.58
     things
    0.58
    Activations Density 0.270%

    No Known Activations