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. 4-GEMMASCOPE-RES-16K
    6. 832
    Prev
    Next
    INDEX
    Explanations

    instances of the word "several."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rego
    -0.80
    zuki
    -0.69
     prez
    -0.67
     it
    -0.66
    anthes
    -0.66
     Olms
    -0.65
     Waltham
    -0.63
     Miki
    -0.63
     Adonis
    -0.63
     Franke
    -0.62
    POSITIVE LOGITS
    several
    1.76
     several
    1.74
    Several
    1.71
     Several
    1.71
     Plusieurs
    1.54
     ſeveral
    1.43
     mehrerer
    1.38
     feveral
    1.35
     dozen
    1.34
     varios
    1.32
    Activations Density 0.091%

    No Known Activations