© 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. 19-GEMMASCOPE-RES-16K
    11. 4623
    Prev
    Next
    INDEX
    Explanations

    patterns or structures in mathematical or scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NameInMap
    -0.70
    webElementGuid
    -0.59
    writeFieldEnd
    -0.55
    ↵↵
    -0.53
    else
    -0.49
    ỏng
    -0.48
    SaveChangesAsync
    -0.47
    MessageOf
    -0.46
    keyColumn
    -0.45
    Analyzed
    -0.45
    POSITIVE LOGITS
    \{\\
    0.81
     виправивши
    0.80
     fallu
    0.70
    ReusableCell
    0.67
    GEBURTS
    0.65
     محفوظة
    0.65
     препратки
    0.64
    ramienta
    0.64
    Enllaces
    0.63
     AssemblyCompany
    0.60
    Activations Density 0.051%

    No Known Activations