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. 11199
    Prev
    Next
    INDEX
    Explanations

    frequency of the word "just."

    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
    первых
    -0.63
    Eileen
    -0.61
    FlatAppearance
    -0.60
    );}
    -0.59
     поколения
    -0.57
     Numerade
    -0.57
    以来
    -0.55
    stärke
    -0.55
     ?>>
    -0.55
     Exe
    -0.54
    POSITIVE LOGITS
    JUST
    0.84
     JUST
    0.80
     Justine
    0.80
     barely
    0.77
     Just
    0.76
    just
    0.73
    Just
    0.73
    ीक
    0.72
    alnız
    0.70
     лишь
    0.69
    Activations Density 0.128%

    No Known Activations