© 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. 28-GEMMASCOPE-RES-16K
    11. 5285
    Prev
    Next
    INDEX
    Explanations

    phrases related to human experiences and conditions

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

    Preceding common verbs or auxiliary verbs

    np_acts-logits-general · gemini-2.0-flash

    actually

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     obviously
    -0.70
     informée
    -0.70
     الرياضيه
    -0.68
    obviously
    -0.65
     Obviously
    -0.64
     tentu
    -0.64
     oczywiście
    -0.63
    Obviously
    -0.62
     ovviamente
    -0.60
     sappiamo
    -0.60
    POSITIVE LOGITS
     actually
    0.51
     وأن
    0.47
    actually
    0.44
     indeed
    0.43
     ACTUALLY
    0.42
     inderdaad
    0.42
     somehow
    0.41
    Actually
    0.37
     "
    0.37
     Actually
    0.37
    Activations Density 0.895%

    No Known Activations