© 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. 15-GEMMASCOPE-RES-16K
    11. 1395
    Prev
    Next
    INDEX
    Explanations

    elements related to organizational strategies and audience targeting

    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
     Majefty
    -1.05
     pleaſure
    -0.96
    ſelves
    -0.94
     nakalista
    -0.93
     greateſt
    -0.92
     myſelf
    -0.90
     Reſ
    -0.89
     ſeveral
    -0.88
     Jefus
    -0.88
    ſelf
    -0.87
    POSITIVE LOGITS
     we
    1.13
     that
    1.11
     you
    0.96
     they
    0.91
     he
    0.81
     she
    0.71
     I
    0.70
     which
    0.69
     to
    0.63
     it
    0.59
    Activations Density 0.294%

    No Known Activations