© 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. 102253
    Prev
    Next
    INDEX
    Explanations

    references to specific types of information or data, particularly regarding numerical or categorical details

    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
    findpost
    -0.75
    <unused41>
    -0.69
    <unused55>
    -0.68
    <unused3>
    -0.68
    <unused42>
    -0.68
    <unused28>
    -0.68
    <unused40>
    -0.68
    <unused16>
    -0.68
    [@BOS@]
    -0.68
    <unused14>
    -0.68
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.41
    ❋
    0.39
    ″]
    0.36
    balleur
    0.32
    estinian
    0.31
     gezegd
    0.31
    GEBURTS
    0.30
    Espèce
    0.30
     AssemblyCompany
    0.30
    ]<=
    0.29
    Activations Density 0.027%

    No Known Activations