© 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. 17-GEMMASCOPE-RES-16K
    6. 8423
    Prev
    Next
    INDEX
    Explanations

    terms related to equipment and technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tikang
    -0.75
     nakalista
    -0.71
     itſelf
    -0.69
     Italijani
    -0.67
    expandindo
    -0.67
     Lordships
    -0.65
     hObject
    -0.63
     Paglinawan
    -0.60
     Nere
    -0.59
     neceffary
    -0.59
    POSITIVE LOGITS
    apimachinery
    0.61
    ')[
    0.54
    afficheront
    0.51
    ArgsConstructor
    0.49
    ser
    0.47
    Jedis
    0.45
    enschappelijke
    0.45
    engah
    0.44
     full
    0.44
     Ser
    0.43
    Activations Density 0.629%

    No Known Activations