© 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. 24-GEMMASCOPE-RES-16K
    11. 14406
    Prev
    Next
    INDEX
    Explanations

    keywords related to legal processes and courtroom details

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

    Precedes the word "were."

    np_acts-logits-general · gemini-2.0-flash

    followed by were

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     was
    -1.19
     is
    -1.00
    was
    -0.97
     isn
    -0.92
     wasn
    -0.86
     wordt
    -0.84
     έχει
    -0.83
     has
    -0.83
    wasn
    -0.76
     doesn
    -0.74
    POSITIVE LOGITS
     were
    2.78
    were
    2.03
    Were
    2.00
     Were
    1.95
     WERE
    1.84
     weren
    1.65
     étaient
    1.23
     waren
    1.23
     były
    1.20
     fueron
    1.20
    Activations Density 0.889%

    No Known Activations