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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 8822
    Prev
    Next
    INDEX
    Explanations

    instances of the word "letters" and 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 @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InputTagHelper
    -0.64
    */),
    -0.56
    دانشنامهٔ
    -0.52
    roaches
    -0.51
    borne
    -0.50
     vervol
    -0.50
     ivelany
    -0.50
    unar
    -0.49
    IntoConstraints
    -0.49
    findpost
    -0.48
    POSITIVE LOGITS
     letters
    0.59
     mar
    0.57
     letter
    0.55
     Letters
    0.52
     LETTERS
    0.51
    Letters
    0.51
     select
    0.49
     recipe
    0.47
     lettere
    0.46
     LETTER
    0.46
    Activations Density 0.363%

    No Known Activations