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-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 857
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notation related to limits, convergence, and boundedness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    mathematical variables and constants denoted with special LaTeX symbols.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.68
    djangoproject
    -0.54
    Tembelea
    -0.52
    tagHelperRunner
    -0.50
    writeField
    -0.50
     oprot
    -0.49
     '\\;'
    -0.47
    цездатний
    -0.47
    Хьажоргаш
    -0.46
    EFIAPI
    -0.45
    POSITIVE LOGITS
     nonzero
    1.27
     positive
    1.26
     >
    1.11
    positive
    1.10
    Positive
    1.03
    nonzero
    1.03
     Positive
    1.01
     $>
    0.99
     POSITIVE
    0.95
     positiven
    0.91
    Activations Density 1.083%

    No Known Activations