© 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. 10049
    Prev
    Next
    INDEX
    Explanations

    phrases related to concepts and ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     certificación
    -0.43
     čast
    -0.42
    Composição
    -0.42
     Comprometido
    -0.41
     régulier
    -0.41
    AfterEach
    -0.41
    orologio
    -0.41
    𝗾
    -0.40
     anglick
    -0.40
     estadísticas
    -0.39
    POSITIVE LOGITS
     Idea
    1.46
    Idea
    1.44
     idea
    1.41
    idea
    1.40
     IDEA
    1.39
     Ideas
    1.37
    Ideas
    1.35
    ideas
    1.34
     ideas
    1.33
    IDEA
    1.23
    Activations Density 0.041%

    No Known Activations