© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 3646
    Prev
    Next
    INDEX
    Explanations

    references to online services and educational resources

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

    appearing before or relating to "online"

    np_acts-logits-general · gemini-2.0-flash

    online and offline contexts

    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
    Spécification
    -0.36
     चाह
    -0.35
    Exemples
    -0.32
    ]")]
    -0.31
     Especific
    -0.31
     gdyby
    -0.31
    Especificación
    -0.31
     Aufg
    -0.31
     aliento
    -0.31
    阶级
    -0.30
    POSITIVE LOGITS
     fashiola
    0.71
     Offline
    0.70
    Offline
    0.67
    GOTREF
    0.66
    ﹧
    0.66
    存于互联网档案馆
    0.65
     queſta
    0.64
    <unused74>
    0.64
    <unused41>
    0.64
    <unused17>
    0.64
    Activations Density 0.065%

    No Known Activations