© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 12321
    Prev
    Next
    INDEX
    Explanations

    phrases or instructions involving "how to" followed by actions or tasks

    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
    ^(@)
    -1.10
     Monfieur
    -1.02
     $_"
    -1.00
     myſelf
    -1.00
     ―――
    -0.97
     ―――――
    -0.97
    BibitemShut
    -0.97
     itſelf
    -0.95
     ProtoMessage
    -0.93
    OGND
    -0.92
    POSITIVE LOGITS
     to
    0.84
    <eos>
    0.79
    :
    0.68
    ↵↵
    0.66
     To
    0.64
    ↵
    0.61
    .
    0.61
     
    0.58
    best
    0.57
    ?
    0.57
    Activations Density 0.258%

    No Known Activations