© 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. 783
    Prev
    Next
    INDEX
    Explanations

    detailed references to scientific terms and entities, particularly in microbial and viral contexts

    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
     vapa
    -0.60
     ilman
    -0.49
     suun
    -0.45
    mybatisplus
    -0.44
     Suomessa
    -0.44
     vaih
    -0.43
     ddelweddau
    -0.43
     vastaan
    -0.42
     ilmo
    -0.42
     näytte
    -0.42
    POSITIVE LOGITS
     KD
    1.34
     KT
    1.34
     KS
    1.33
     KF
    1.33
     KK
    1.33
     KP
    1.33
     K
    1.31
     KB
    1.30
    KS
    1.26
    K
    1.26
    Activations Density 12.727%

    No Known Activations