© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 7768
    Prev
    Next
    INDEX
    Explanations

    patterns related to technical specifications and operations in computer hardware

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code related to I2C

    np_acts-logits-general · gemini-2.0-flash

    i2c, pci, C

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ngrx
    -0.65
    flashdata
    -0.64
     resourceCulture
    -0.61
    verwijspagina
    -0.61
    HostException
    -0.57
    CastException
    -0.56
    rungsseite
    -0.56
    oneph
    -0.53
    AxisAlignment
    -0.52
    исленность
    -0.51
    POSITIVE LOGITS
    örté
    0.66
     Cæsar
    0.62
     ſeveral
    0.61
     препратки
    0.59
     مشارکت‌کنندگان
    0.55
     Shakspeare
    0.55
     purpoſe
    0.53
     shur
    0.53
     ویکی‌پدیای
    0.52
     esternos
    0.52
    Activations Density 0.618%

    No Known Activations