© 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. 10670
    Prev
    Next
    INDEX
    Explanations

    structure definitions and code-related expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    complex computational code involving numerical array operations, dataset construction, and geometric transformations.

    oai_token-act-pair · o3-miniTriggered by @yemengyus1
    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
     string
    -0.69
     name
    -0.68
     id
    -0.64
     object
    -0.62
     void
    -0.62
     json
    -0.62
     function
    -0.62
     type
    -0.61
     data
    -0.61
     url
    -0.60
    POSITIVE LOGITS
     mediocrity
    0.53
     prostitu
    0.51
     masaj
    0.49
     financiar
    0.46
     fotbal
    0.46
     intellectually
    0.45
     unilaterally
    0.45
     automobil
    0.45
     humiliated
    0.45
     teatral
    0.45
    Activations Density 13.396%

    No Known Activations