© 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. 14-GEMMASCOPE-RES-16K
    11. 510
    Prev
    Next
    INDEX
    Explanations

    special formatting or structural elements in text, such as brackets and quotation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewImports
    -0.56
     ++)
    -0.55
     ervan
    -0.53
    脚注の使い方
    -0.52
     hierfür
    -0.50
    SuccessListener
    -0.50
    pulos
    -0.49
     impres
    -0.49
    itemBuilder
    -0.48
    CompleteListener
    -0.46
    POSITIVE LOGITS
    RUnlock
    0.60
     propOrder
    0.57
    第二
    0.52
    RetentionPolicy
    0.52
     AttributeSet
    0.50
     zweiter
    0.48
     第二
    0.48
     ModelExpression
    0.47
    URSS
    0.47
     høj
    0.47
    Activations Density 1.104%

    No Known Activations