© 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. 15-GEMMASCOPE-RES-16K
    6. 1551
    Prev
    Next
    INDEX
    Explanations

    references to various classifications and categories across different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -0.67
    AndEndTag
    -0.54
     estekak
    -0.53
     nahilalakip
    -0.48
    andExpect
    -0.47
    Hentet
    -0.44
    Tikang
    -0.44
    RTDA
    -0.42
     jScrollPane
    -0.42
     שוליים
    -0.41
    POSITIVE LOGITS
    Various
    1.06
     Various
    1.05
     various
    1.05
     olika
    1.03
    Different
    1.02
     different
    1.01
     مختلف
    1.01
    various
    1.00
     Different
    0.99
     różne
    0.98
    Activations Density 0.689%

    No Known Activations