© 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-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 101601
    Prev
    Next
    INDEX
    Explanations

    nested expressions and greater-than/less-than symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    urlopen
    -0.47
    esModule
    -0.43
    ardon
    -0.42
    WebMethod
    -0.41
    ruptedException
    -0.41
    ActionPerformed
    -0.40
     ParseException
    -0.40
    iostream
    -0.40
    structors
    -0.40
    URLException
    -0.40
    POSITIVE LOGITS
    ISupport
    0.59
     defaultstate
    0.59
    EndInit
    0.58
    Diweddarwch
    0.57
     tartalomajánló
    0.54
    országban
    0.52
    )(((
    0.51
    CppMethod
    0.50
    BeginInit
    0.50
     Roskov
    0.49
    Activations Density 0.001%

    No Known Activations