© 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 - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 14911
    Prev
    Next
    INDEX
    Explanations

    phrases relating to inequality and disparity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewImports
    -0.62
    roh
    -0.49
    xions
    -0.48
     corte
    -0.47
    Auguste
    -0.47
    covering
    -0.47
     boca
    -0.47
    ljeno
    -0.47
    宛
    -0.46
    ########.
    -0.46
    POSITIVE LOGITS
    AxisAlignment
    0.66
    IntoConstraints
    0.63
     BytesLike
    0.62
     TextInputType
    0.60
    TestingModule
    0.59
     فريبيس
    0.59
    TagMode
    0.57
    енча
    0.56
    ModelBuilder
    0.56
    QMetaType
    0.55
    Activations Density 0.136%

    No Known Activations