© 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. 1-GEMMASCOPE-RES-16K
    6. 8180
    Prev
    Next
    INDEX
    Explanations

    HTML tags, especially headers, in markup language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EoL
    -0.62
     climatique
    -0.59
    illère
    -0.57
     Messina
    -0.57
    ilogue
    -0.56
     Fontana
    -0.55
    ediat
    -0.55
     lye
    -0.55
     klim
    -0.55
     Beal
    -0.55
    POSITIVE LOGITS
    header
    1.18
    HasAnnotation
    0.85
    InstanceState
    0.80
    site
    0.76
    évaluateur
    0.75
    ]))
    
    0.73
    matchCondition
    0.70
    (...)
    0.69
    /**
    0.68
    mergeFrom
    0.67
    Activations Density 0.106%

    No Known Activations