Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 2970
    Prev
    Next
    INDEX
    Explanations

    specific cultural or ethnic references and musical terminology

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

    references to specific cultural items or practices

    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
    rália
    -0.51
    ggars
    -0.43
     betweenstory
    -0.42
    ÁT
    -0.40
    chute
    -0.40
    ttino
    -0.40
    áját
    -0.38
    瑩
    -0.37
    cestershire
    -0.37
     zw
    -0.37
    POSITIVE LOGITS
    contentLoaded
    0.56
     AssemblyTitle
    0.49
    migrations
    0.45
    enderror
    0.44
     ve
    0.44
    İ
    0.44
    Merhaba
    0.42
    nın
    0.40
    ileri
    0.40
     veya
    0.39
    Activations Density 0.079%

    No Known Activations