© 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. 1-GEMMASCOPE-RES-16K
    6. 2516
    Prev
    Next
    INDEX
    Explanations

    words related to bold formatting and the concept of spin in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Fuhr
    -0.44
     Lindgren
    -0.44
    recated
    -0.44
     Zinn
    -0.44
    fieldLabel
    -0.43
     Seidel
    -0.42
     caneca
    -0.41
     sih
    -0.41
     trade
    -0.40
     upgrade
    -0.40
    POSITIVE LOGITS
     Bold
    0.69
    Bold
    0.60
     bold
    0.58
     boldly
    0.56
     BOLD
    0.54
     estekak
    0.52
     Spinner
    0.52
    Optical
    0.51
    BOLD
    0.50
     spinach
    0.50
    Activations Density 0.393%

    No Known Activations