© 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. 2853
    Prev
    Next
    INDEX
    Explanations

    a combination of alphanumeric characters and special symbols often associated with coding or data structures

    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
    الثة
    -0.57
    enderror
    -0.57
     viewDidLoad
    -0.55
     nineteen
    -0.54
    لاث
    -0.53
     الثلاث
    -0.53
     seventeenth
    -0.48
    chehen
    -0.47
    UrlResolution
    -0.47
    viewDidLoad
    -0.46
    POSITIVE LOGITS
    8
    2.03
     eight
    1.59
     Eight
    1.55
     Eighth
    1.46
     eighth
    1.44
     EIGHT
    1.37
    8
    1.33
    八
    1.31
    Eight
    1.29
     delapan
    1.29
    Activations Density 2.721%

    No Known Activations