© 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. 16-GEMMASCOPE-RES-16K
    11. 7155
    Prev
    Next
    INDEX
    Explanations

    constructed programming elements related to loop and condition structures

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

    Code-related tokens: variables, loops, and conditions

    np_acts-logits-general · gemini-2.0-flash

    programming loop control keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مشين
    -0.64
     صوتيه
    -0.60
     ProtoMessage
    -0.54
     bew
    -0.54
    Carriera
    -0.47
    resc
    -0.47
    ابراین
    -0.47
     only
    -0.45
    IconModule
    -0.45
     def
    -0.44
    POSITIVE LOGITS
     Cæsar
    0.67
     doInBackground
    0.66
     StringTokenizer
    0.65
    CAPTION
    0.64
    PYX
    0.63
    IntoConstraints
    0.62
     cathédrale
    0.61
    AxisAlignment
    0.59
     ModelRenderer
    0.59
    aguya
    0.59
    Activations Density 0.040%

    No Known Activations