© 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. 3-GEMMASCOPE-RES-16K
    11. 5770
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names, particularly in the context of musicians and orchestras

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    #+#
    -0.63
    ImageContext
    -0.59
    soever
    -0.57
     CommandType
    -0.53
    +#+
    -0.50
    httphttps
    -0.49
     betweenstory
    -0.49
     IMDG
    -0.49
     Valence
    -0.49
    putan
    -0.49
    POSITIVE LOGITS
    mybatisplus
    0.83
     violinist
    0.76
     orchestra
    0.74
    Piano
    0.73
    webElementXpaths
    0.68
     Orchestra
    0.67
     Piano
    0.67
     Symphony
    0.65
     Violin
    0.64
     piano
    0.64
    Activations Density 0.381%

    No Known Activations