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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 10888
    Prev
    Next
    INDEX
    Explanations

    comparative or superlative adjectives and phrases indicating size, quantity, or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Efq
    -0.90
     Monfieur
    -0.84
     vectorstock
    -0.79
     Jefus
    -0.78
     ſeveral
    -0.77
     iſt
    -0.76
     doubtnut
    -0.75
     myſelf
    -0.75
    BibitemShut
    -0.73
     Theſe
    -0.72
    POSITIVE LOGITS
     than
    2.08
    than
    1.47
     THAN
    1.33
     niż
    1.25
    Than
    1.22
     Than
    1.20
     než
    1.05
     kuin
    0.98
     än
    0.88
    THAN
    0.78
    Activations Density 0.435%

    No Known Activations