© 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. 22-GEMMASCOPE-RES-16K
    11. 12646
    Prev
    Next
    INDEX
    Explanations

    terms related to legal actions and proceedings, particularly those involving charges and allegations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Preceding words of "against"

    np_acts-logits-general · gemini-2.0-flash

    action against

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ujednoznacz
    -0.67
    DoubleQuotes
    -0.64
    \{\\
    -0.61
    enumi
    -0.55
    AnchorStyles
    -0.54
    batore
    -0.54
    howe
    -0.54
    JsonHelper
    -0.52
     насељу
    -0.49
     Himo
    -0.49
    POSITIVE LOGITS
     against
    4.42
    against
    3.79
     Against
    3.67
    Against
    3.57
     AGAINST
    3.20
     contre
    2.86
     gegen
    2.86
     tegen
    2.48
     против
    2.47
     melawan
    2.37
    Activations Density 1.164%

    No Known Activations