© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 4727
    Prev
    Next
    INDEX
    Explanations

    references to machine learning and its applications

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

    "Machine" or "mechan" prefixes

    np_acts-logits-general · gemini-2.0-flash

    machine learning

    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
     AIAA
    -0.80
    RetentionPolicy
    -0.78
    IntoConstraints
    -0.76
     étage
    -0.69
    Slf
    -0.68
    toastr
    -0.67
    endsection
    -0.66
    тьяна
    -0.66
    ✭✭
    -0.66
     IOP
    -0.64
    POSITIVE LOGITS
    Mechanisms
    1.08
     Mechanisms
    0.96
    mechan
    0.94
     mechanisms
    0.93
     MECHAN
    0.92
     mechan
    0.85
     machinery
    0.84
    MECHAN
    0.83
     mécan
    0.82
     mechanism
    0.80
    Activations Density 0.090%

    No Known Activations