© 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. 5-GEMMASCOPE-RES-16K
    11. 3207
    Prev
    Next
    INDEX
    Explanations

    references to corresponding items or values in a scientific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sidemargin
    -0.63
    AxisAlignment
    -0.63
    phosa
    -0.58
     AppCompatTheme
    -0.55
    klaim
    -0.52
     nltk
    -0.52
     scrollView
    -0.50
     walking
    -0.48
    ссора
    -0.48
     newItem
    -0.48
    POSITIVE LOGITS
     corresponding
    1.33
    corresponding
    1.20
    Corresponding
    1.08
     Corresponding
    1.06
     respective
    1.04
     entsprechende
    1.03
     correspondiente
    1.02
     relevant
    1.00
    相应
    1.00
     entsprechenden
    1.00
    Activations Density 0.374%

    No Known Activations