Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 12164
    Prev
    Next
    INDEX
    Explanations

    words related to completing or finishing processes

    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
     leef
    -0.45
     xlink
    -0.43
    ByDefault
    -0.41
     dirección
    -0.40
     Sanz
    -0.40
    card
    -0.39
     berlaku
    -0.39
     vectores
    -0.39
     ampio
    -0.39
    cal
    -0.39
    POSITIVE LOGITS
     finishing
    1.85
     finish
    1.72
     finishes
    1.65
    Finishing
    1.62
     Finishing
    1.61
    finishing
    1.61
     finished
    1.59
    finished
    1.54
     Finish
    1.53
     Finished
    1.52
    Activations Density 0.251%

    No Known Activations