© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 8472
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "forms" or variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     geblieben
    -0.47
    cão
    -0.46
    :][
    -0.43
    nicity
    -0.41
    tagHelperRunner
    -0.41
    __["
    -0.40
     ſtate
    -0.40
     '../../
    -0.40
    harp
    -0.40
     seyn
    -0.40
    POSITIVE LOGITS
    Forms
    1.11
    forms
    1.09
     forms
    0.99
     Forms
    0.98
     FORMS
    0.93
    FORMS
    0.79
     formes
    0.66
     formas
    0.60
     vormen
    0.57
     форм
    0.57
    Activations Density 0.034%

    No Known Activations