© 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 - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 514
    Prev
    Next
    INDEX
    Explanations

    medical terms related to cancer and its impacts

    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
     betweenstory
    -0.66
    enterOuterAlt
    -0.58
    TemporalType
    -0.57
    WithIOException
    -0.54
    tanooga
    -0.54
    LVANIA
    -0.53
    CodeAnalysis
    -0.52
    VersionUID
    -0.52
     <>",
    -0.52
    ValueGeneration
    -0.51
    POSITIVE LOGITS
     global
    2.42
     worldwide
    2.36
     globally
    2.11
    global
    2.03
    worldwide
    1.87
    全球
    1.86
     mondial
    1.86
     Global
    1.80
     weltweit
    1.79
     international
    1.73
    Activations Density 0.889%

    No Known Activations