© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 936
    Prev
    Next
    INDEX
    Explanations

    complex sentence structures and dependencies in communication

    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
    •Steering evals
    french

    No Comments

    Negative Logits
     Pública
    -0.48
     Byd
    -0.47
     Económica
    -0.46
     Ersten
    -0.45
     uſe
    -0.44
    TypedDataSet
    -0.44
     Sigism
    -0.43
     ſhould
    -0.43
     themſelves
    -0.43
     groupId
    -0.42
    POSITIVE LOGITS
     faire
    0.74
     être
    0.68
     mettre
    0.67
     avoir
    0.65
     prendre
    0.65
     jouer
    0.62
     réaliser
    0.62
     tenir
    0.62
     mener
    0.62
     rendre
    0.62
    Activations Density 0.075%

    No Known Activations