© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 9563
    Prev
    Next
    INDEX
    Explanations

    elements related to programming syntax and structure

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

    CSS and code syntax highlighting class names and markup.

    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
     mergeFrom
    -0.59
     resourceCulture
    -0.57
    SequentialGroup
    -0.54
    новништво
    -0.52
    CodedInputStream
    -0.51
     насељу
    -0.47
    ModelState
    -0.47
    omitempty
    -0.46
     propOrder
    -0.45
    DIPSETTING
    -0.44
    POSITIVE LOGITS
     reserved
    0.98
     special
    0.91
     symbols
    0.85
     keywords
    0.81
     keyword
    0.78
     operators
    0.78
    Reserved
    0.77
    reserved
    0.77
    special
    0.76
     symbol
    0.74
    Activations Density 1.440%

    No Known Activations