© 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 - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 6787
    Prev
    Next
    INDEX
    Explanations

    musical compositions and performances of specific classical works and orchestras

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

    key musical works and performances by composers

    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
    ulturen
    -0.54
    Насе
    -0.52
    twimg
    -0.51
     ProtoMessage
    -0.50
    ensiva
    -0.50
     cultura
    -0.50
    IsMutable
    -0.49
    MethodImpl
    -0.49
    ursing
    -0.49
     dressing
    -0.48
    POSITIVE LOGITS
     Suite
    0.67
     Variations
    0.65
    RegressionTest
    0.65
     suite
    0.64
     Andante
    0.64
     suites
    0.64
     Suites
    0.62
     Adagio
    0.61
     Sonata
    0.59
     op
    0.57
    Activations Density 0.220%

    No Known Activations