© 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. 2-GEMMASCOPE-RES-16K
    11. 15451
    Prev
    Next
    INDEX
    Explanations

    U-shaped configurations or patterns in data or experimental results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RectangleBorder
    -0.74
    StoryboardSegue
    -0.70
     שוליים
    -0.65
    Diweddarwch
    -0.64
     Audiodateien
    -0.64
     विश्वसनीयता
    -0.60
    цезда
    -0.60
    intenant
    -0.60
    rehensive
    -0.59
    Hentet
    -0.56
    POSITIVE LOGITS
    DllImport
    0.73
    erschein
    0.52
    ewski
    0.52
    <eos>
    0.50
    jsonwebtoken
    0.48
     hormigón
    0.48
    quared
    0.48
     tű
    0.48
     szabály
    0.47
     munc
    0.47
    Activations Density 0.731%

    No Known Activations