© 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. 33-GEMMASCOPE-RES-16K
    11. 11079
    Prev
    Next
    INDEX
    Explanations

    measurements and characteristics related to molecular structures and dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     musées
    -0.40
     conférences
    -0.40
    文件的
    -0.40
    libros
    -0.38
     navires
    -0.37
     outils
    -0.36
     jouets
    -0.35
     prêtres
    -0.35
    Projects
    -0.35
    experiments
    -0.35
    POSITIVE LOGITS
     sizes
    1.31
     widths
    1.28
     names
    1.20
     thicknesses
    1.20
     lengths
    1.20
     intensities
    1.17
     speeds
    1.16
     durations
    1.16
     diameters
    1.15
     weights
    1.13
    Activations Density 1.957%

    No Known Activations