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

    Neuronpedia

    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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 5569
    Prev
    Next
    INDEX
    Explanations

    references to well-known names and recognizability

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

    Follows "of", "hosted", or indicates level of awareness

    np_acts-logits-general · gemini-2.0-flash

    names and notoriety

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     predicted
    -0.37
     disfruta
    -0.36
    ReusableCell
    -0.34
    UnusedPrivate
    -0.34
     Garuda
    -0.33
     BoxFit
    -0.32
    Explicación
    -0.32
     disponíveis
    -0.32
     समीक्षक
    -0.32
    GenerationType
    -0.32
    POSITIVE LOGITS
    извест
    0.53
     notoriety
    0.52
    知っている
    0.50
    odori
    0.48
     household
    0.48
    awareness
    0.48
     Unknown
    0.48
    Awareness
    0.47
     notori
    0.47
     unknown
    0.47
    Activations Density 0.266%

    No Known Activations