© 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. 8692
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing exclusivity or particularity

    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
     either
    -0.79
     anche
    -0.78
    both
    -0.78
     entrambi
    -0.75
     Either
    -0.75
     even
    -0.74
     both
    -0.73
    Either
    -0.71
     ambos
    -0.70
    either
    -0.69
    POSITIVE LOGITS
     estekak
    0.84
    RectangleBorder
    0.84
    mybatisplus
    0.81
     sondern
    0.80
     ProtoMessage
    0.74
     myſelf
    0.73
    CloseOperation
    0.73
     becauſe
    0.72
     iſt
    0.71
     itſelf
    0.71
    Activations Density 0.079%

    No Known Activations