Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 19-GEMMASCOPE-RES-16K
    6. 11310
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal proceedings and judicial outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PreferredItem
    -0.69
    UIControlState
    -0.63
     bezeichneter
    -0.56
    enapa
    -0.54
    createCanvas
    -0.53
    acán
    -0.52
    ViewInit
    -0.52
     pinulongan
    -0.51
     whatever
    -0.50
    下载附件
    -0.49
    POSITIVE LOGITS
    Recently
    1.17
     Recently
    1.16
     בשנת
    1.16
     Yesterday
    1.13
    Yesterday
    1.11
     Shortly
    1.10
     летом
    1.07
    During
    1.07
     Earlier
    1.05
     весной
    1.05
    Activations Density 0.550%

    No Known Activations