© 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. 18-GEMMASCOPE-RES-16K
    11. 1835
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax, specifically around function definitions and public/private modifiers

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

    Swift code related to protobuf messages

    np_acts-logits-general · gemini-2.0-flash

    Swift code declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PerformLayout
    -1.09
     CreateTagHelper
    -1.08
    aarrggbb
    -0.96
    ArgsConstructor
    -0.88
    TintMode
    -0.88
    featureID
    -0.86
    endphp
    -0.83
    GOTREF
    -0.80
     oprot
    -0.80
     unknownFields
    -0.80
    POSITIVE LOGITS
    ↵↵
    0.65
    <eos>
    0.63
     den
    0.53
    public
    0.52
     
    0.48
    ↵
    0.47
     pr
    0.45
    ,
    0.44
     You
    0.44
    expandindo
    0.44
    Activations Density 0.046%

    No Known Activations