© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 7863
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names and titles

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

    Tokens before "zotto" or after "ia"

    np_acts-logits-general · gemini-2.0-flash

    giazotto, Riazuddin, Nia

    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
    cluse
    -0.56
    lankton
    -0.56
     biết
    -0.51
    Zeneca
    -0.49
    itosti
    -0.48
    estacks
    -0.48
     oportun
    -0.48
    étit
    -0.48
    هاز
    -0.48
    entant
    -0.48
    POSITIVE LOGITS
     Nia
    0.92
    pia
    0.82
     كومونز
    0.79
    Ria
    0.74
    IUrlHelper
    0.73
     SIA
    0.73
    出版年
    0.72
    Cia
    0.72
     Ria
    0.71
    Demografía
    0.71
    Activations Density 0.180%

    No Known Activations