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. 3-GEMMASCOPE-RES-16K
    6. 12304
    Prev
    Next
    INDEX
    Explanations

    terms related to technical and scientific subjects, particularly in the context of data modeling and statistical analysis

    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
    ValueStyle
    -0.81
     Bex
    -0.76
     Opa
    -0.74
     argent
    -0.72
    IBar
    -0.71
     Eko
    -0.71
    DotNetBar
    -0.69
     Lancer
    -0.68
     Michaelis
    -0.68
     OAS
    -0.68
    POSITIVE LOGITS
    ubus
    0.93
     Nuss
    0.90
    uuuu
    0.90
     Ruz
    0.87
    ZU
    0.85
     Huf
    0.84
    upu
    0.84
     Bus
    0.83
    uuu
    0.83
    uu
    0.83
    Activations Density 2.501%

    No Known Activations