© 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. 0-GEMMASCOPE-RES-16K
    11. 9974
    Prev
    Next
    INDEX
    Explanations

    expressions of liking or disliking toward various subjects or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LookAnd
    -1.00
     MainAxisSize
    -0.89
    
    -0.83
     يتيمه
    -0.81
    ConstraintMaker
    -0.80
     تانيه
    -0.77
    wapV
    -0.76
    CppCodeGen
    -0.75
     gouvernements
    -0.75
     sondern
    -0.74
    POSITIVE LOGITS
    </td>
    0.59
     liked
    0.54
     fore
    0.53
     LIK
    0.48
     similar
    0.48
    .(
    0.47
     vermo
    0.47
     relevant
    0.47
     apro
    0.47
     outstanding
    0.47
    Activations Density 0.230%

    No Known Activations