© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 13-GEMMASCOPE-RES-16K
    6. 6360
    Prev
    Next
    INDEX
    Explanations

    phrases that express appreciation or admiration for ideas and qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cura
    -0.61
     handleMessage
    -0.56
     cæ
    -0.51
    qtt
    -0.51
     dAtA
    -0.50
    kshake
    -0.48
     Balancing
    -0.47
    AIRE
    -0.47
    ης
    -0.47
    AIRES
    -0.47
    POSITIVE LOGITS
    mybatisplus
    0.81
     but
    0.80
    出版年
    0.67
     pourtant
    0.62
     nhưng
    0.61
     namun
    0.58
     lunghezza
    0.58
     tetapi
    0.58
     Paglinawan
    0.58
     但是
    0.56
    Activations Density 0.557%

    No Known Activations