Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 8764
    Prev
    Next
    INDEX
    Explanations

    numerical values or quantities related to measurements

    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
    -0.72
     a
    -0.70
     R
    -0.64
     C
    -0.62
     Mc
    -0.62
     O
    -0.61
     The
    -0.60
     V
    -0.59
     c
    -0.59
     deux
    -0.59
    POSITIVE LOGITS
     ―――――
    1.24
     ſche
    1.23
    )");
    
    1.20
    Datuak
    1.19
     myſelf
    1.18
     Majefty
    1.17
     itſelf
    1.16
     dieß
    1.16
     ſtate
    1.14
     purpoſe
    1.13
    Activations Density 0.586%

    No Known Activations