© 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. 3625
    Prev
    Next
    INDEX
    Explanations

    statements that present a significant claim or observation in the text

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

    the word "This" at the beginning of sentences that introduce explanations or consequences.

    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
     thingy
    -0.46
     noDo
    -0.46
     niggas
    -0.45
     Planners
    -0.43
    bungen
    -0.41
     dudes
    -0.41
    GIRLS
    -0.41
     bruno
    -0.40
    bufio
    -0.40
    hashtags
    -0.39
    POSITIVE LOGITS
    Autoritní
    0.88
    webElementXpaths
    0.77
     otomatig
    0.69
     ब्रेकडाउन
    0.62
     same
    0.62
     includes
    0.59
     contrasts
    0.56
     samma
    0.54
     latter
    0.53
     wiederum
    0.52
    Activations Density 0.407%

    No Known Activations