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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 12755
    Prev
    Next
    INDEX
    Explanations

    numerical data related to measurements or statistics

    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
    featureID
    -0.93
     transfieras
    -0.89
    };*/
    -0.79
    parsedMessage
    -0.76
     незавершена
    -0.75
    ̈́
    -0.75
     EconPapers
    -0.75
     nahilalakip
    -0.73
    #+#
    -0.73
     مشين
    -0.72
    POSITIVE LOGITS
    ,
    0.68
     NgModule
    0.45
    ths
    0.42
     //
    0.41
    paramref
    0.41
    .
    0.41
    Ẽ
    0.41
    </strong>
    0.39
     deti
    0.38
    癸
    0.38
    Activations Density 0.155%

    No Known Activations