© 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. 4953
    Prev
    Next
    INDEX
    Explanations

    Arabic script and symbols relating to geography or urban locations

    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
     kasarigan
    -1.08
    abestanden
    -1.05
    writeFieldEnd
    -1.02
    Autoritní
    -1.01
    parsedMessage
    -0.99
     تضيفلها
    -0.97
     kaarangay
    -0.95
     виправивши
    -0.95
    Geplaatst
    -0.95
     doInBackground
    -0.93
    POSITIVE LOGITS
     يتيمه
    0.78
     a
    0.55
     Atlántico
    0.50
     an
    0.50
     sää
    0.49
    اد
    0.46
    ----------
    0.46
     ق
    0.46
    ußer
    0.45
     menyenangkan
    0.45
    Activations Density 0.010%

    No Known Activations