© 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. 8-GEMMASCOPE-RES-16K
    11. 14695
    Prev
    Next
    INDEX
    Explanations

    numerical values, particularly those represented as fractions or decimals, often in mathematical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     A
    -0.70
     The
    -0.68
    maco
    -0.64
     C
    -0.64
      
    -0.64
     qu
    -0.62
    tC
    -0.62
     Two
    -0.61
     F
    -0.61
     a
    -0.60
    POSITIVE LOGITS
    Datuak
    1.31
     ―――――
    1.24
     dieß
    1.23
     Majefty
    1.19
     ſche
    1.11
     myſelf
    1.11
     ISNI
    1.11
     Diretto
    1.10
     itſelf
    1.08
     Diſ
    1.04
    Activations Density 0.488%

    No Known Activations