© 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. 18-GEMMASCOPE-RES-16K
    11. 8358
    Prev
    Next
    INDEX
    Explanations

    specific numerical or mathematical data related to time and dates

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

    Followed by a digit

    np_acts-logits-general · gemini-2.0-flash

    programming code and dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wikimedijinoj
    -0.67
     الاطلاع
    -0.67
     Vikipedi
    -0.66
    SuppressMessage
    -0.64
    
    -0.62
    InjectAttribute
    -0.61
    mybatisplus
    -0.60
     الحره
    -0.59
    mercato
    -0.57
     ContentValues
    -0.55
    POSITIVE LOGITS
    ÁB
    0.56
    ')['
    0.51
    enus
    0.48
     vgl
    0.47
     plant
    0.47
     throws
    0.47
    ENTION
    0.47
    setCharacter
    0.47
    ]!='
    0.47
     Plo
    0.46
    Activations Density 0.387%

    No Known Activations