© 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. 3-GEMMASCOPE-RES-16K
    11. 8076
    Prev
    Next
    INDEX
    Explanations

    phrases indicating expectations or future actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ^(@)
    -0.92
     Efq
    -0.86
    adaptiveStyles
    -0.83
     Jefus
    -0.83
     cdti
    -0.79
     Houſe
    -0.77
    SBATCH
    -0.77
     للمعارف
    -0.76
    InitVars
    -0.75
     $_"
    -0.74
    POSITIVE LOGITS
     according
    1.62
    according
    1.53
    According
    1.51
     According
    1.47
    Según
    1.42
     selon
    1.35
     Selon
    1.34
     Secondo
    1.32
     Según
    1.30
    Selon
    1.30
    Activations Density 0.112%

    No Known Activations