© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 8778
    Prev
    Next
    INDEX
    Explanations

    phrases related to dramatic situations and transformations in life

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

    sudden or dramatic changes in circumstances or situations.

    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
     jScrollPane
    -0.60
    Tembelea
    -0.55
    MLLoader
    -0.54
     endblock
    -0.54
    WriteBarrier
    -0.53
    tvguidetime
    -0.52
    DockStyle
    -0.51
    AISSEE
    -0.50
    addPreferredGap
    -0.49
    titleMargin
    -0.49
    POSITIVE LOGITS
     when
    3.50
     quando
    2.77
     cuando
    2.73
    when
    2.70
     когда
    2.58
     When
    2.25
    When
    2.23
     lorsque
    2.23
     WHEN
    2.22
     kiedy
    2.22
    Activations Density 3.048%

    No Known Activations