© 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. 34-GEMMASCOPE-RES-16K
    11. 11114
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical appearances and characteristics of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ciment
    -0.41
    imenta
    -0.38
    antaranya
    -0.36
     sampah
    -0.35
     funcionando
    -0.35
    luia
    -0.35
    פן
    -0.34
     infierno
    -0.34
     pelajaran
    -0.34
     cordes
    -0.33
    POSITIVE LOGITS
     tall
    1.61
     taller
    1.41
    tall
    1.37
     skinny
    1.34
     slender
    1.25
    Tall
    1.23
     tallest
    1.20
     chubby
    1.19
     Tall
    1.17
     slim
    1.13
    Activations Density 0.559%

    No Known Activations