© 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. 2260
    Prev
    Next
    INDEX
    Explanations

    sentences that convey positive evaluations or experiences

    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
    Przypisy
    -0.63
    ̣i
    -0.57
    rophore
    -0.54
     dernières
    -0.52
    ValueStyle
    -0.51
    shafen
    -0.51
     tarvit
    -0.51
     varsa
    -0.51
    كذا
    -0.50
     الدولى
    -0.49
    POSITIVE LOGITS
     quite
    2.88
    quite
    2.48
     very
    2.48
     fairly
    2.29
     Quite
    2.27
     pretty
    2.24
    Quite
    2.21
     bastante
    2.06
    very
    1.95
     khá
    1.91
    Activations Density 1.273%

    No Known Activations