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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 3314
    Prev
    Next
    INDEX
    Explanations

    elements and attributes related to programming syntax, particularly in JSON and HTML/XML structures

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

    numerical values and parameters in structured code and configuration files.

    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
     indígen
    -0.63
    ⓧ
    -0.58
    IContainer
    -0.58
     desmotivaciones
    -0.56
    +#+
    -0.54
     nonUne
    -0.54
    راتيج
    -0.54
     creș
    -0.54
    исленность
    -0.53
     대한민
    -0.52
    POSITIVE LOGITS
    Tikang
    0.37
    bewerken
    0.37
    DockStyle
    0.34
    以上就是
    0.32
    richTextPanel
    0.30
    Бележки
    0.30
    kháu
    0.29
    weightedMode
    0.29
    ″]
    0.29
     ​​
    0.28
    Activations Density 1.887%

    No Known Activations