© 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-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 12587
    Prev
    Next
    INDEX
    Explanations

    phrases indicating disagreement or criticism, particularly in the context of political discourse

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

    Negative or critical remarks

    np_acts-logits-general · gemini-2.0-flash

    veiled/stinging/blunt comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IUrlHelper
    -0.80
    ValueStyle
    -0.58
    تفصیلات
    -0.57
     EconPapers
    -0.57
     rencont
    -0.57
    getMenuInflater
    -0.56
     épreuve
    -0.56
     fortæller
    -0.53
     beginnetje
    -0.52
     pulumi
    -0.52
    POSITIVE LOGITS
     veiled
    0.86
     remarks
    0.77
     stinging
    0.75
     oblique
    0.73
     blunt
    0.72
     comments
    0.70
     rejo
    0.70
     thinly
    0.67
     coded
    0.67
     barbed
    0.67
    Activations Density 0.454%

    No Known Activations