© 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. 15-GEMMASCOPE-RES-16K
    6. 1953
    Prev
    Next
    INDEX
    Explanations

    references to time periods or comparisons between different time frames

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     complètes
    -0.68
     Folly
    -0.65
    تفصیلات
    -0.65
     lähe
    -0.61
     Cæsar
    -0.61
     HEC
    -0.61
     Tacitus
    -0.60
     ioe
    -0.59
     russa
    -0.58
     RSSSF
    -0.58
    POSITIVE LOGITS
     Between
    1.52
    between
    1.51
     between
    1.49
     BETWEEN
    1.46
    Between
    1.45
    BETWEEN
    1.40
     zwischen
    1.29
     betweenstory
    1.28
     entre
    1.25
     tussen
    1.24
    Activations Density 0.143%

    No Known Activations