© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 34-GEMMASCOPE-RES-16K
    6. 11308
    Prev
    Next
    INDEX
    Explanations

    terms related to medical and biological conditions involving "pal" in their structure or context

    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
     estekak
    -0.56
    Tembelea
    -0.49
    تقاوى
    -0.47
     betweenstory
    -0.45
     kaarangay
    -0.44
     EconPapers
    -0.42
     fol
    -0.42
    #+#
    -0.41
     wireType
    -0.39
     Existence
    -0.39
    POSITIVE LOGITS
    Pal
    0.92
     Pal
    0.90
     pal
    0.85
     PAL
    0.83
    PAL
    0.81
    pal
    0.79
    Palmar
    0.63
     Pala
    0.63
     Palette
    0.62
     pallet
    0.62
    Activations Density 0.086%

    No Known Activations