© 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. 21-GEMMASCOPE-RES-16K
    11. 12726
    Prev
    Next
    INDEX
    Explanations

    repeated instances of the word "so" emphasizing a point or sentiment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stretchr
    -0.48
    הערות
    -0.48
    lanan
    -0.48
    μία
    -0.47
    UN
    -0.46
    unes
    -0.46
    /*---
    -0.46
    LatLng
    -0.45
     üzere
    -0.45
    Amérique
    -0.45
    POSITIVE LOGITS
     far
    1.03
     much
    0.94
    othed
    0.89
    ckeye
    0.89
     they
    0.84
    called
    0.73
     we
    0.70
    }();
    0.68
    UnknownFieldSet
    0.66
    Much
    0.65
    Activations Density 0.083%

    No Known Activations