© 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. 3620
    Prev
    Next
    INDEX
    Explanations

    phrases that imply legal issues or consequences

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

    Follows "was" and indicates a negative event

    np_acts-logits-general · gemini-2.0-flash

    was + negative event

    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
    withOpacity
    -0.48
    nyataan
    -0.48
    __*/
    -0.47
     êtres
    -0.46
     spørs
    -0.45
     ricor
    -0.43
     souffrance
    -0.42
     paham
    -0.41
     vanske
    -0.40
    masalahan
    -0.40
    POSITIVE LOGITS
     arrested
    1.25
     killed
    1.07
     shot
    1.04
     murdered
    1.04
     sentenced
    1.01
     stabbed
    1.00
     kidnapped
    0.99
     caught
    0.97
     deported
    0.96
     knocked
    0.95
    Activations Density 0.400%

    No Known Activations