© 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. 2-GEMMASCOPE-RES-16K
    6. 14724
    Prev
    Next
    INDEX
    Explanations

    technical terms and identifiers in code related to programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     túl
    -0.49
     purpoſe
    -0.49
     regeringen
    -0.47
     chrétiens
    -0.46
     quæ
    -0.46
     scuro
    -0.46
     AUTHORS
    -0.46
     partout
    -0.45
    étranger
    -0.45
    Authors
    -0.45
    POSITIVE LOGITS
    cshtml
    0.79
    "];
    
    0.73
    irlo
    0.71
    IntoConstraints
    0.70
     linkovi
    0.68
    tagHelper
    0.67
    ir
    0.66
     विश्वसनीयता
    0.64
    tvguidetime
    0.62
    "]
    
    0.61
    Activations Density 1.932%

    No Known Activations