Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 34-GEMMASCOPE-RES-16K
    6. 10781
    Prev
    Next
    INDEX
    Explanations

    medical terms related to spinal injuries and conditions

    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
     <=",
    -0.51
    arcoma
    -0.39
     onPostExecute
    -0.38
     caldera
    -0.38
    adaptiveStyles
    -0.37
     ویکی‌پدیا
    -0.37
     Einfluß
    -0.37
     ritard
    -0.36
    TDS
    -0.35
     voeren
    -0.35
    POSITIVE LOGITS
     spine
    1.20
     spinal
    1.15
     Spine
    1.09
     vertebrae
    1.05
     Spinal
    1.01
     vertebral
    0.99
    Spine
    0.96
     vertebra
    0.95
    spinal
    0.95
    spine
    0.93
    Activations Density 0.350%

    No Known Activations