© 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. 21-GEMMASCOPE-RES-16K
    11. 2636
    Prev
    Next
    INDEX
    Explanations

    verbs and phrases that suggest caution or concern regarding actions and their consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     its
    -0.98
     Its
    -0.92
     Оно
    -0.92
    Its
    -0.90
     thereof
    -0.85
     therefrom
    -0.78
     therein
    -0.73
    DoubleQuotes
    -0.70
     thereon
    -0.69
     thereunder
    -0.69
    POSITIVE LOGITS
     it
    1.39
    It
    1.02
    it
    0.96
     It
    0.86
     IT
    0.65
     itr
    0.56
    IT
    0.52
    itm
    0.52
    इट
    0.48
    usercontent
    0.46
    Activations Density 0.388%

    No Known Activations