© 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. 3305
    Prev
    Next
    INDEX
    Explanations

    items and concepts related to daily life and personal experiences

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

    The token before years

    np_acts-logits-general · gemini-2.0-flash

    noun followed by related noun

    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
     مشين
    -1.10
     ainfi
    -1.01
     quelcon
    -1.01
     feroit
    -0.97
     zelve
    -0.97
     stället
    -0.96
     chré
    -0.96
     complètes
    -0.95
     plufieurs
    -0.95
     enfans
    -0.94
    POSITIVE LOGITS
     tax
    0.67
    -
    0.63
     pro
    0.63
     bar
    0.62
     re
    0.61
     tra
    0.61
     and
    0.60
    ():
    0.59
    /
    0.58
     mas
    0.58
    Activations Density 1.175%

    No Known Activations