© 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-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 4474
    Prev
    Next
    INDEX
    Explanations

    instances of the word "form" and its variations, indicating a focus on formation or creation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Keegan
    -0.64
    ikations
    -0.63
    aughter
    -0.62
    ennium
    -0.62
     Cáceres
    -0.60
     NCC
    -0.60
     valves
    -0.60
    lihood
    -0.60
    rceil
    -0.59
    signee
    -0.59
    POSITIVE LOGITS
     FORM
    1.45
     Forms
    1.32
     Forma
    1.29
     Form
    1.29
     forms
    1.23
    form
    1.21
     FORMS
    1.19
    FORM
    1.16
    Form
    1.16
     form
    1.14
    Activations Density 0.187%

    No Known Activations