© 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. 15500
    Prev
    Next
    INDEX
    Explanations

    topics related to introductions and biographical information

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

    Tokens preceding "the author" or "about"

    np_acts-logits-general · gemini-2.0-flash

    about [subject/person]

    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
    CppMethod
    -0.89
    tanleria
    -0.88
    aspectj
    -0.84
     Shakspeare
    -0.80
    EndContext
    -0.79
    WithIOException
    -0.79
    (&:
    -0.79
     Shaksp
    -0.79
    AddTagHelper
    -0.78
    NUMX
    -0.77
    POSITIVE LOGITS
     the
    0.79
     this
    0.68
     author
    0.67
    :
    0.64
     our
    0.62
     us
    0.60
     me
    0.58
    作者
    0.56
     Author
    0.55
    author
    0.54
    Activations Density 0.171%

    No Known Activations