Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 12631
    Prev
    Next
    INDEX
    Explanations

    Java class definitions and their structure

    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
    Rüyada
    -0.83
    AsUp
    -0.80
     himo
    -0.80
     Houſe
    -0.78
    цездатний
    -0.77
     चीज़ों
    -0.77
    RenderAtEndOf
    -0.77
     Италијани
    -0.77
    TintMode
    -0.77
    AutoScaleMode
    -0.76
    POSITIVE LOGITS
     Pas
    0.50
    วย
    0.47
    رار
    0.46
    Khal
    0.46
    ksz
    0.46
     représenter
    0.45
     concevoir
    0.45
     Des
    0.45
    clearInterval
    0.44
    кер
    0.44
    Activations Density 0.018%

    No Known Activations