© 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. 4-GEMMASCOPE-RES-16K
    11. 15603
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and quotation marks indicating dialogue or speech

    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
     hom
    -0.65
    kháu
    -0.61
     *
    -0.55
     cons
    -0.55
     Veld
    -0.55
     sto
    -0.54
    adget
    -0.54
     bal
    -0.54
     Hodges
    -0.53
    aan
    -0.52
    POSITIVE LOGITS
    .’”
    0.90
    ,’’
    0.83
    sizeCache
    0.81
    。“
    0.81
    ,’”
    0.81
    、“
    0.79
    ’;
    0.78
    ，“
    0.77
     fermés
    0.76
     firſt
    0.75
    Activations Density 0.482%

    No Known Activations