© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 34-GEMMASCOPE-RES-16K
    6. 7730
    Prev
    Next
    INDEX
    Explanations

    names of individuals involved in a legal case

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    httphttps
    -0.81
     surla
    -0.76
     allAfrica
    -0.58
    XmlEnum
    -0.58
     Gorb
    -0.57
     Inoue
    -0.55
    +#+#
    -0.54
     propOrder
    -0.54
     Roskov
    -0.53
     ModelRenderer
    -0.53
    POSITIVE LOGITS
     Strain
    0.42
     Young
    0.42
     Welsh
    0.40
     Logs
    0.40
     ſind
    0.40
     dezelve
    0.40
     Spinner
    0.39
     traceback
    0.39
     Null
    0.39
     Shader
    0.39
    Activations Density 0.286%

    No Known Activations