© 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. 14-GEMMASCOPE-RES-16K
    6. 6797
    Prev
    Next
    INDEX
    Explanations

    syntax elements in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ніципалі
    -0.62
     hard
    -0.53
     cra
    -0.52
     Nes
    -0.52
     plots
    -0.51
    plot
    -0.51
    böz
    -0.51
     Plot
    -0.50
     Lijst
    -0.49
     Hard
    -0.48
    POSITIVE LOGITS
    ArgsConstructor
    0.91
    AddTagHelper
    0.74
     nahilalakip
    0.73
    AccessorTable
    0.73
    iconque
    0.71
    InSection
    0.69
     extranjeros
    0.69
     combien
    0.66
    enumi
    0.66
    __':
    
    0.65
    Activations Density 0.021%

    No Known Activations