© 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. 15-GEMMASCOPE-RES-16K
    11. 1264
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to procedural arguments and court rulings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lic
    -0.45
    TableHead
    -0.44
     toute
    -0.43
     FUCK
    -0.42
    IonicModule
    -0.42
    द
    -0.42
     ['./
    -0.41
     fuck
    -0.40
    zburg
    -0.40
    fuck
    -0.40
    POSITIVE LOGITS
     myſelf
    0.94
     itſelf
    0.94
     Efq
    0.93
    DockStyle
    0.89
     pleaſure
    0.86
     ―――――
    0.85
    +#+#
    0.83
     faſt
    0.79
    ſelves
    0.79
     againſt
    0.79
    Activations Density 0.636%

    No Known Activations