© 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. 21-GEMMASCOPE-RES-16K
    11. 10819
    Prev
    Next
    INDEX
    Explanations

    instances of the word "register" and its variations, indicating a focus on registration processes or requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ayuda
    -0.51
    Monday
    -0.49
    comida
    -0.49
    cpp
    -0.49
    Réponse
    -0.49
     Milán
    -0.47
    primaryColor
    -0.46
     Woody
    -0.46
     Holanda
    -0.46
    util
    -0.46
    POSITIVE LOGITS
     register
    1.20
     registration
    1.09
     Register
    1.07
     registering
    1.02
     Regist
    1.02
     registers
    1.01
     REGISTER
    1.00
     regist
    0.99
     registered
    0.98
    register
    0.98
    Activations Density 0.204%

    No Known Activations