© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 4501
    Prev
    Next
    INDEX
    Explanations

    references to educational policies and legal proceedings related to students with disabilities

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

    Criticism or pointing out flaws

    np_acts-logits-general · gemini-2.0-flash

    absence, failure, or omission

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resourceCulture
    -0.82
    Portail
    -0.76
     Beſ
    -0.72
    MemoryWarning
    -0.72
     myſelf
    -0.71
     wikipagina
    -0.71
    انيف
    -0.70
    iastes
    -0.70
     Theſe
    -0.68
     itſelf
    -0.67
    POSITIVE LOGITS
     without
    1.26
     lack
    1.15
     neglect
    1.13
     lacks
    1.10
     unaware
    1.09
     lacked
    1.08
     ignoring
    1.07
     neglecting
    1.07
     ignored
    1.07
     neglected
    1.06
    Activations Density 0.994%

    No Known Activations