© 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. 7-GEMMASCOPE-RES-16K
    11. 6743
    Prev
    Next
    INDEX
    Explanations

    references to directories or file paths, particularly in a programming or software development context

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

    references to file paths or repositories in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyTitle
    -0.87
    windowFixed
    -0.72
    RTEX
    -0.72
    StoryboardSegue
    -0.69
     '\\;'
    -0.66
    parsedMessage
    -0.58
    bcryptjs
    -0.58
    WillAppear
    -0.57
     }));
    -0.52
     awakeFromNib
    -0.51
    POSITIVE LOGITS
    WebVitals
    0.77
    bootstrapcdn
    0.72
    فحة
    0.60
    doctype
    0.60
    dymyr
    0.60
     Haar
    0.59
     "..\..\
    0.59
     UNF
    0.58
    DOCTYPE
    0.58
     незавершена
    0.58
    Activations Density 0.078%

    No Known Activations