© 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. 5-GEMMASCOPE-RES-16K
    11. 14072
    Prev
    Next
    INDEX
    Explanations

    terms related to legal processes and considerations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     myſelf
    -1.38
    ſelf
    -1.31
    ſelves
    -1.29
     initComponents
    -1.28
     itſelf
    -1.27
     Efq
    -1.20
     whoſe
    -1.17
     оригіналу
    -1.16
     raiſ
    -1.14
     Jefus
    -1.13
    POSITIVE LOGITS
    <eos>
    0.64
     
    0.58
     the
    0.54
    -
    0.54
    ,
    0.54
    </i>
    0.53
    .
    0.51
     la
    0.49
     a
    0.49
     "
    0.46
    Activations Density 0.802%

    No Known Activations