© 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-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 1338
    Prev
    Next
    INDEX
    Explanations

    discussed limitations or disadvantages of a process or condition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nemmeno
    -0.60
    AddTagHelper
    -0.56
    下载附件
    -0.53
     tampoco
    -0.53
     pesar
    -0.53
     useAppContext
    -0.52
     ioutil
    -0.52
     unknownFields
    -0.52
    ostic
    -0.51
     iff
    -0.50
    POSITIVE LOGITS
     among
    2.18
     Among
    2.03
    among
    1.97
    Among
    1.93
     amongst
    1.82
     AMONG
    1.74
     Amongst
    1.72
     blant
    1.51
     antaranya
    1.49
     parmi
    1.42
    Activations Density 0.335%

    No Known Activations