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. 8035
    Prev
    Next
    INDEX
    Explanations

    instances of the word "gather" and its variations, indicating a focus on collecting or assembling information or groups

    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
     Meksiku
    -0.84
     <
    -0.54
    adaptiveStyles
    -0.53
     yii
    -0.52
    SystemColors
    -0.52
     ==
    -0.51
    getChildAt
    -0.51
    /*
    -0.51
    Зноскі
    -0.50
     Sinha
    -0.50
    POSITIVE LOGITS
     Gather
    1.73
     gathering
    1.65
     gathers
    1.63
    Gather
    1.57
     gather
    1.56
     gathered
    1.51
     Gathering
    1.47
    gathering
    1.45
    Gathering
    1.40
     accumulating
    1.37
    Activations Density 0.268%

    No Known Activations