© 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. 11-GEMMASCOPE-RES-16K
    6. 13661
    Prev
    Next
    INDEX
    Explanations

    references to physical constants or quantitative measurements in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     изд
    -0.49
    orum
    -0.47
     ch
    -0.46
    ..
    -0.46
    <eos>
    -0.45
     فري
    -0.45
    lsch
    -0.44
     index
    -0.44
     Abdel
    -0.44
    asci
    -0.44
    POSITIVE LOGITS
    tagHelperRunner
    0.85
    adpleegd
    0.85
     '\\;'
    0.81
     يتيمه
    0.80
    reszcie
    0.79
    neté
    0.78
    setVerticalGroup
    0.77
     myſelf
    0.76
    Portail
    0.76
     AssemblyCompany
    0.75
    Activations Density 0.808%

    No Known Activations