© 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. 33-GEMMASCOPE-RES-16K
    11. 11161
    Prev
    Next
    INDEX
    Explanations

    mention of wars and conflicts, particularly in regions like Iraq, Afghanistan, and others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RTLR
    -0.53
    fillType
    -0.52
     BorderSide
    -0.50
    findpost
    -0.49
    DIPSETTING
    -0.49
    richTextPanel
    -0.47
    XmlAccessorType
    -0.46
    EndGlobalSection
    -0.46
    StructEnd
    -0.46
     myſelf
    -0.45
    POSITIVE LOGITS
     Afghanistan
    1.18
     Iraq
    1.00
     Afgan
    0.94
     Syria
    0.90
    Afghanistan
    0.88
     conflicts
    0.88
     Yemen
    0.88
     Afghan
    0.87
     Libya
    0.81
    Iraq
    0.81
    Activations Density 0.305%

    No Known Activations