© 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. 23-GEMMASCOPE-RES-16K
    11. 14573
    Prev
    Next
    INDEX
    Explanations

    phrases related to quality and performance assessments in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     виправивши
    -0.50
     niks
    -0.48
    again
    -0.48
     gì
    -0.46
    quite
    -0.45
     niets
    -0.45
     assez
    -0.44
    ありません
    -0.44
     lisää
    -0.44
     bastante
    -0.43
    POSITIVE LOGITS
     each
    1.82
     poszczegól
    1.44
    each
    1.34
     einzelnen
    1.28
     chaque
    1.28
     EACH
    1.25
    Each
    1.25
     Each
    1.22
     masing
    1.21
     jednotliv
    1.17
    Activations Density 1.429%

    No Known Activations