© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 3636
    Prev
    Next
    INDEX
    Explanations

    phrases related to direct actions and procedural steps

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Directly" or words with similar meaning

    np_acts-logits-general · gemini-2.0-flash

    straight to or skipping

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lapsingToolbar
    -0.46
    scriptcase
    -0.43
    setViewportView
    -0.40
     OFDb
    -0.39
     corpo
    -0.39
    Rüyada
    -0.38
    MENAFN
    -0.37
    ChildScrollView
    -0.35
     jspb
    -0.34
     semif
    -0.34
    POSITIVE LOGITS
     skipping
    1.02
     directly
    1.01
     Directly
    0.98
    directly
    0.96
     direct
    0.93
     skip
    0.92
    直接
    0.88
    Direct
    0.88
     directamente
    0.87
     сразу
    0.87
    Activations Density 0.458%

    No Known Activations