© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 8746
    Prev
    Next
    INDEX
    Explanations

    references to tricks or clever methods

    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
    Witam
    -0.44
     autorytatywna
    -0.43
     mulighed
    -0.43
    phosa
    -0.42
    écrivain
    -0.42
     irgendwann
    -0.41
    incontro
    -0.41
     faudra
    -0.40
     informatique
    -0.40
     Ultimately
    -0.40
    POSITIVE LOGITS
     challenging
    1.18
     Challenging
    1.02
    chall
    0.92
    Chall
    0.91
    complex
    0.81
    Complex
    0.75
     Complex
    0.74
     complex
    0.74
     Challenger
    0.70
     COMPLEX
    0.68
    Activations Density 0.058%

    No Known Activations