© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 15597
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific or technical specifications and measurements

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

    "Spec" followed by a variety of endings

    np_acts-logits-general · gemini-2.0-flash

    words starting with spec or spect

    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
    omla
    -0.72
     onCreateView
    -0.69
    fromCharCode
    -0.68
    ಿನ
    -0.64
     resourceCulture
    -0.63
     оригіналу
    -0.62
    ompi
    -0.59
    clips
    -0.58
    oporosis
    -0.58
    lawayo
    -0.58
    POSITIVE LOGITS
     Speck
    0.84
     spec
    0.84
     SPEC
    0.83
     Spec
    0.82
    SPEC
    0.79
    Spec
    0.78
     Spectre
    0.75
    spec
    0.74
    pec
    0.72
    참고
    0.68
    Activations Density 0.120%

    No Known Activations