Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 8415
    Prev
    Next
    INDEX
    Explanations

    repetitive use of the word "every" in various contexts, indicating a focus on common experiences or universal truths

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCompany
    -0.73
    UnusedPrivate
    -0.61
    GEBURTSDATUM
    -0.60
    Референце
    -0.59
    CppMethod
    -0.59
    ollectionView
    -0.58
     StatefulWidget
    -0.57
     invokingState
    -0.55
    XmlAccessorType
    -0.55
     HttpNotFound
    -0.54
    POSITIVE LOGITS
     single
    1.23
    ones
    1.11
     conceivable
    1.06
    single
    0.92
    things
    0.90
     imaginable
    0.89
    bod
    0.83
    bodies
    0.82
     other
    0.79
    BODY
    0.79
    Activations Density 0.068%

    No Known Activations