© 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-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 594
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "appropriate" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الحره
    -0.75
    rboles
    -0.73
    expandindo
    -0.71
    FieldBuilder
    -0.69
    Jensen
    -0.69
     فريبيس
    -0.68
    crowned
    -0.66
    γχ
    -0.65
     незавершена
    -0.65
    RunWith
    -0.65
    POSITIVE LOGITS
    Appropriate
    1.94
     appropriate
    1.93
     Appropriate
    1.89
    appropriate
    1.77
    nappropriate
    1.65
     APPROPRI
    1.63
     appropriately
    1.57
     appropri
    1.53
     appropriateness
    1.51
     Appropri
    1.48
    Activations Density 0.093%

    No Known Activations