© 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. 4-GEMMASCOPE-RES-16K
    6. 2895
    Prev
    Next
    INDEX
    Explanations

    data related to numerical values or mathematical expressions

    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
    ंदीखरीदारी
    -1.13
     defaultstate
    -0.97
    ."]
    -0.95
    \}\\
    -0.92
     bezeichneter
    -0.90
    "]];
    -0.89
    "]));
    -0.88
    LikeLiked
    -0.87
    XmlAccessType
    -0.84
    uxxxx
    -0.83
    POSITIVE LOGITS
    rxjs
    0.57
    Spoljašnje
    0.55
    7
    0.53
     thị
    0.51
     Kline
    0.50
     чу
    0.48
    峙
    0.48
    edy
    0.48
    izmu
    0.48
    Cornell
    0.48
    Activations Density 0.532%

    No Known Activations