© 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. 20-GEMMASCOPE-RES-16K
    11. 1813
    Prev
    Next
    INDEX
    Explanations

    the word "full" in various contexts related to completeness or total evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases including the word "full" across various contexts like technical documentation, legal descriptions, and research reports.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ocasião
    -0.52
     debilidad
    -0.47
     Städte
    -0.47
     conductores
    -0.46
     זאת
    -0.46
     Mice
    -0.45
     apuestas
    -0.45
     Schick
    -0.45
     votación
    -0.44
     pájaros
    -0.43
    POSITIVE LOGITS
     Full
    1.35
    Full
    1.33
     full
    1.28
     FULL
    1.17
    FULL
    1.09
    full
    1.07
    isFull
    0.99
     fuller
    0.90
    getFull
    0.89
     fullName
    0.81
    Activations Density 0.049%

    No Known Activations