© 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-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 13377
    Prev
    Next
    INDEX
    Explanations

    references to rotation or rotating mechanisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     otomatig
    -0.45
     incó
    -0.41
     незавершена
    -0.41
    бият
    -0.40
     ritratto
    -0.40
     yük
    -0.39
    󠁢
    -0.38
    antası
    -0.38
    cosystem
    -0.38
    เอง
    -0.38
    POSITIVE LOGITS
     rot
    1.17
     Rot
    0.96
    rot
    0.89
    Rot
    0.86
     corrupt
    0.66
     ROT
    0.65
     Kat
    0.63
     Kab
    0.63
    pulumi
    0.62
     rotting
    0.62
    Activations Density 0.646%

    No Known Activations