© 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. 2-GEMMASCOPE-RES-16K
    11. 8699
    Prev
    Next
    INDEX
    Explanations

    words related to physical pain and emotional distress

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    webElementXpaths
    -0.58
    HomeAsUpEnabled
    -0.54
    StackNavigator
    -0.50
    TagMode
    -0.47
    DIPSETTING
    -0.47
     Proz
    -0.47
     Paglinawan
    -0.47
     Normdatei
    -0.46
    Портали
    -0.46
     /\.(
    -0.46
    POSITIVE LOGITS
     hurt
    2.78
    hurt
    2.31
     hurts
    2.09
     Hurt
    1.98
     injury
    1.94
     injured
    1.91
     injuries
    1.90
     injure
    1.88
     hurting
    1.86
    Hurt
    1.84
    Activations Density 0.190%

    No Known Activations