© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 14860
    Prev
    Next
    INDEX
    Explanations

    connections to legal and procedural terminology

    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
     time
    -3.11
     Time
    -2.51
    time
    -2.50
    Time
    -2.42
     TIME
    -2.34
    TIME
    -2.10
     times
    -2.01
     tijd
    -1.84
    时间
    -1.84
     Zeit
    -1.83
    POSITIVE LOGITS
     виправивши
    0.52
     disambiguazione
    0.49
    רח
    0.41
     ويكيميديا
    0.41
    zzlement
    0.41
     platelets
    0.40
    teng
    0.39
     Normdatei
    0.38
    يكب
    0.38
     Dusche
    0.36
    Activations Density 1.176%

    No Known Activations