© 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. 15-GEMMASCOPE-RES-16K
    11. 1245
    Prev
    Next
    INDEX
    Explanations

    specific biochemical or pharmacological terms and components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     per
    -0.45
    化的
    -0.45
    ...
    -0.43
    <eos>
    -0.42
     material
    -0.41
     temu
    -0.39
     a
    -0.39
     motor
    -0.39
    Q
    -0.39
    sel
    -0.39
    POSITIVE LOGITS
    TagMode
    1.00
     snippetHide
    0.89
     Majefty
    0.85
     ChromeDriver
    0.80
     Monfieur
    0.80
     Efq
    0.80
     AssemblyCompany
    0.79
     myſelf
    0.76
     avoient
    0.76
    RegistryLite
    0.75
    Activations Density 1.086%

    No Known Activations