© 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. 15330
    Prev
    Next
    INDEX
    Explanations

    instances of the term "name" and its variations within a text

    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
    utnik
    -0.38
    reloadData
    -0.37
     Deliber
    -0.35
     vidare
    -0.34
    rebel
    -0.33
    stiff
    -0.33
     JSTOR
    -0.33
    spectrum
    -0.32
     Sol
    -0.30
     dalamnya
    -0.30
    POSITIVE LOGITS
    plate
    0.74
    plates
    0.71
     Name
    0.70
     NAME
    0.68
    rungsseite
    0.65
    txtName
    0.64
    NAME
    0.61
    Surname
    0.61
     Names
    0.61
     names
    0.61
    Activations Density 0.126%

    No Known Activations