© 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-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 6512
    Prev
    Next
    INDEX
    Explanations

    references to physical locations and objects within a setting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tainable
    -0.57
    ädie
    -0.56
    dorff
    -0.55
    apunov
    -0.54
    期刊论文
    -0.54
    __);
    -0.54
    ])).
    -0.53
    acionais
    -0.53
    Décès
    -0.49
    digm
    -0.49
    POSITIVE LOGITS
     lenker
    0.75
     للمعارف
    0.74
    StoryboardSegue
    0.73
    bootstrapcdn
    0.70
     estekak
    0.68
    PreferredItem
    0.61
    CppCodeGen
    0.57
    windowFixed
    0.56
    ItemBackground
    0.56
    Clik
    0.54
    Activations Density 0.310%

    No Known Activations