© 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. 2435
    Prev
    Next
    INDEX
    Explanations

    expressions related to deception or hidden truths

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

    before periods or prepositions

    np_acts-logits-general · gemini-2.0-flash

    figurative idioms and common phrases

    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
    IVIA
    -0.55
    ']?>
    -0.53
    '];?>
    -0.53
    RESUMEN
    -0.51
    "]="
    -0.50
    }`)
    -0.49
    GEE
    -0.49
     stb
    -0.48
    mybatisplus
    -0.47
    hideLoading
    -0.47
    POSITIVE LOGITS
     regarding
    0.78
     figur
    0.69
     concernant
    0.67
     proverbial
    0.67
     betweenstory
    0.63
     concerning
    0.63
     kaarangay
    0.63
     financially
    0.61
    fjspx
    0.61
     musically
    0.59
    Activations Density 0.365%

    No Known Activations