© 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. 9789
    Prev
    Next
    INDEX
    Explanations

    references to news agencies and their reporting

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

    Acronyms for news agencies

    np_acts-logits-general · gemini-2.0-flash

    news agencies

    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
    úrese
    -0.54
    jarkan
    -0.42
    Vorlage
    -0.41
     cận
    -0.40
     kela
    -0.40
    SCR
    -0.40
    likle
    -0.39
    anggap
    -0.38
    core
    -0.38
     التن
    -0.38
    POSITIVE LOGITS
     Agencies
    0.88
    ########.
    0.84
    KommentareTeilen
    0.77
    Agencies
    0.77
     agencies
    0.76
     dpa
    0.74
    JspWriter
    0.74
     HasFactory
    0.74
     Agency
    0.73
     Agencia
    0.72
    Activations Density 0.058%

    No Known Activations