© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 8756
    Prev
    Next
    INDEX
    Explanations

    present tense forms of the verb "to be" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kullanılır
    -0.35
    -------------</
    -0.33
    と思った
    -0.31
     uwe
    -0.30
     initComponents
    -0.29
    と思いました
    -0.27
     ambiguity
    -0.27
    <?
    -0.26
    ingly
    -0.26
    CreateModel
    -0.26
    POSITIVE LOGITS
     getting
    1.65
     becoming
    1.61
     taking
    1.50
     making
    1.45
     proving
    1.41
     gaining
    1.40
     happening
    1.39
     behaving
    1.37
     showing
    1.37
     doing
    1.37
    Activations Density 0.668%

    No Known Activations