© 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. 34-GEMMASCOPE-RES-16K
    11. 15418
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "to be" and related verbs indicating states or actions

    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
     kullanılır
    -0.34
    :✨
    -0.32
    gerufen
    -0.31
     denotes
    -0.28
    Introdu
    -0.28
     Défense
    -0.27
     sağlar
    -0.27
    CreateModel
    -0.27
     uwe
    -0.27
    と思った
    -0.26
    POSITIVE LOGITS
     becoming
    1.76
     getting
    1.46
    becoming
    1.41
     being
    1.37
     proving
    1.35
     gaining
    1.32
     growing
    1.25
     coming
    1.18
     happening
    1.18
     evolving
    1.17
    Activations Density 0.569%

    No Known Activations