© 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. 38-GEMMASCOPE-RES-16K
    11. 14791
    Prev
    Next
    INDEX
    Explanations

    phrases that express uncertainty or the potential for personal growth and decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    之助
    -0.34
    awtextra
    -0.33
    waitUntil
    -0.32
     lauk
    -0.32
     líqu
    -0.32
     laim
    -0.32
     impedir
    -0.32
     assurent
    -0.31
     מרו
    -0.31
    無事に
    -0.31
    POSITIVE LOGITS
     delve
    1.39
     dab
    1.22
     dive
    1.18
     diving
    1.16
     mergul
    1.08
     dived
    1.06
     venturing
    1.05
     foray
    1.05
     del
    1.02
     dipping
    1.02
    Activations Density 0.571%

    No Known Activations