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. 3532
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and expressions, particularly those involving functions and variables

    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
    XmlAccessorType
    -0.46
     Schweitzer
    -0.45
     насељу
    -0.45
     Hanford
    -0.42
     Kaka
    -0.41
     Sentinel
    -0.40
     Kalu
    -0.38
    før
    -0.38
     Afonso
    -0.38
     Abb
    -0.38
    POSITIVE LOGITS
     RY
    1.41
     SY
    1.38
     AY
    1.38
     PY
    1.36
     LY
    1.33
    SY
    1.33
    RY
    1.33
    DY
    1.32
     DY
    1.32
     CY
    1.30
    Activations Density 6.218%

    No Known Activations