© 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. 5-GEMMASCOPE-RES-16K
    11. 7790
    Prev
    Next
    INDEX
    Explanations

    technical terms and jargon related to scientific and technological 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
     resto
    -0.52
     bright
    -0.47
     Majefty
    -0.46
    ſelf
    -0.44
    底
    -0.44
    RefNanny
    -0.44
     March
    -0.43
     Houſe
    -0.43
     Vida
    -0.43
    bright
    -0.43
    POSITIVE LOGITS
     تانيه
    0.91
     betweenstory
    0.88
    bootstrapcdn
    0.85
    aarrggbb
    0.83
    andExpect
    0.79
    ThroughAttribute
    0.78
     ddelweddau
    0.77
     dataSnapshot
    0.76
    sizeCache
    0.76
    ########.
    0.75
    Activations Density 2.314%

    No Known Activations