© 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. 10-GEMMASCOPE-RES-16K
    6. 15237
    Prev
    Next
    INDEX
    Explanations

    references to crime and moral dilemmas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/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.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <eos>
    -0.59
     
    -0.58
     I
    -0.55
     «
    -0.54
    ,
    -0.53
     "
    -0.51
     /
    -0.51
    .
    -0.49
     and
    -0.48
     (
    -0.48
    POSITIVE LOGITS
     myſelf
    1.46
    featureID
    1.37
     Monfieur
    1.37
     Reſ
    1.31
     themſelves
    1.28
    ſelves
    1.27
    ſelf
    1.26
     itſelf
    1.25
     ſtate
    1.24
     himſelf
    1.23
    Activations Density 0.767%

    No Known Activations