© 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-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 8064
    Prev
    Next
    INDEX
    Explanations

    instances of the word "trying."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 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
    Datuak
    -0.75
    اریخ
    -0.70
     незавершена
    -0.68
     Dodson
    -0.67
     puissante
    -0.66
     Portail
    -0.65
     mijne
    -0.65
     škoda
    -0.64
     voeten
    -0.64
     precisione
    -0.63
    POSITIVE LOGITS
     trying
    2.23
     Trying
    2.17
    Trying
    2.05
    trying
    2.01
     attempting
    1.28
     tryna
    1.25
     wanting
    1.20
     tries
    1.18
    Tries
    1.03
     looking
    1.01
    Activations Density 0.062%

    No Known Activations