© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 3613
    Prev
    Next
    INDEX
    Explanations

    concepts and discourse surrounding ideas and their formulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Comprometido
    -0.52
    ureusement
    -0.51
    AfterEach
    -0.48
    ristorante
    -0.47
    botines
    -0.47
    orologio
    -0.47
    𝗾
    -0.47
     Montgomery
    -0.47
     estadísticas
    -0.46
     parachoque
    -0.46
    POSITIVE LOGITS
     Idea
    1.38
    Idea
    1.33
     Ideas
    1.32
     idea
    1.31
    Ideas
    1.26
     ideas
    1.26
     IDEA
    1.26
    idea
    1.24
    ideas
    1.23
     IDEAS
    1.13
    Activations Density 0.066%

    No Known Activations