© 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. 2948
    Prev
    Next
    INDEX
    Explanations

    references to organizational or package structures in code

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

    package and class names from Java code, particularly those that include organizational identifiers

    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
    addCriterion
    -0.56
     שוליים
    -0.53
    breviation
    -0.53
    composed
    -0.51
     Composed
    -0.51
     trasc
    -0.49
     InputDecoration
    -0.49
    MessageTagHelper
    -0.48
    وفاته
    -0.48
    Lage
    -0.48
    POSITIVE LOGITS
    asaki
    0.55
    umman
    0.54
     ujednoznacz
    0.53
    terase
    0.47
    üyada
    0.45
    mobileqq
    0.44
    RegressionTest
    0.44
     resourceCulture
    0.43
    MigrationBuilder
    0.43
     defaultstate
    0.43
    Activations Density 0.065%

    No Known Activations