© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 14086
    Prev
    Next
    INDEX
    Explanations

    historical figures and events involving leadership and territorial conflicts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     VizieR
    -0.50
     séance
    -0.49
     Olympia
    -0.47
     remb
    -0.47
     Willkommen
    -0.47
     ellips
    -0.46
    orama
    -0.46
     Burial
    -0.46
     deserialize
    -0.45
    ętr
    -0.45
    POSITIVE LOGITS
     betweenstory
    0.69
    Medieval
    0.69
     Crusade
    0.67
     Medieval
    0.67
     medieval
    0.67
    tagext
    0.65
     knights
    0.63
     Crusaders
    0.63
    下载附件
    0.63
     knight
    0.60
    Activations Density 0.256%

    No Known Activations