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. 11015
    Prev
    Next
    INDEX
    Explanations

    medical conditions and related terminology

    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
    gráficas
    -0.41
     žem
    -0.40
    :✨
    -0.40
    jewództ
    -0.39
     endwhile
    -0.39
     AppCompatTheme
    -0.38
     epidermis
    -0.38
     Skins
    -0.38
    ispiel
    -0.38
    rored
    -0.37
    POSITIVE LOGITS
     tumor
    0.66
     benign
    0.64
     masses
    0.62
     cysts
    0.59
     tumour
    0.59
     cyst
    0.58
     tumors
    0.58
     growths
    0.56
     Masses
    0.55
     tumours
    0.54
    Activations Density 1.073%

    No Known Activations