© 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. 25-GEMMASCOPE-RES-16K
    11. 8809
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to "double" in various contexts, indicating a focus on duality or duplication

    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
    Datuak
    -0.79
    TagMode
    -0.67
     unknownFields
    -0.66
    يكب
    -0.61
    __":
    -0.60
     initComponents
    -0.59
    ViewImports
    -0.59
     [*]
    -0.59
     <<<<<<<<<<<<<<
    -0.55
    __*/
    -0.55
    POSITIVE LOGITS
     decker
    0.78
     entendre
    0.75
     jeopardy
    0.73
     entend
    0.72
    decker
    0.71
     sided
    0.69
     digit
    0.69
     Decker
    0.66
    entendre
    0.65
     Trouble
    0.64
    Activations Density 0.193%

    No Known Activations