© 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. 932
    Prev
    Next
    INDEX
    Explanations

    assertions of opinion or statements about facts

    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
    prefixer
    -0.61
    others
    -0.60
     Baillargeon
    -0.57
    THERE
    -0.56
    there
    -0.56
     đó
    -0.53
    นั้น
    -0.53
     istnieje
    -0.53
    this
    -0.52
     đây
    -0.52
    POSITIVE LOGITS
     why
    1.20
     because
    0.94
     where
    0.93
     how
    0.92
     true
    0.80
     porque
    0.74
     perché
    0.74
     despite
    0.73
    mybatisplus
    0.71
     assuming
    0.70
    Activations Density 0.292%

    No Known Activations