© 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. 11317
    Prev
    Next
    INDEX
    Explanations

    positive feedback about experiences and services

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

    "is" or "was" followed by an adjective

    np_acts-logits-general · gemini-2.0-flash

    states/qualities after 'to be'

    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
     önem
    -0.61
    <bos>
    -0.55
    телен
    -0.46
    장
    -0.46
     gern
    -0.44
     peculi
    -0.43
     gärna
    -0.43
    endency
    -0.43
    บบ
    -0.43
    endencies
    -0.43
    POSITIVE LOGITS
     phenomenal
    0.85
     Roskov
    0.81
     fantastic
    0.81
     outstanding
    0.80
     amazing
    0.76
     wonderful
    0.73
     superb
    0.73
    outstanding
    0.72
    fantastic
    0.71
     exceptional
    0.71
    Activations Density 0.124%

    No Known Activations