© 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 EvalsExportsinterp-engineNEWAPI 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. 10929
    Prev
    Next
    INDEX
    Explanations

    patterns and conditional phrases related to decision-making and preference

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

    Follows a period

    np_acts-logits-general · gemini-2.0-flash

    technical code identifiers

    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
    зю
    -0.58
    Externé
    -0.56
     đăng
    -0.54
     bangun
    -0.53
    XtraGrid
    -0.53
    randi
    -0.53
    것은
    -0.52
    EqualsAnd
    -0.52
     )$
    -0.51
     nenhum
    -0.51
    POSITIVE LOGITS
    XmlRootElement
    0.66
    setVerticalGroup
    0.63
    MessageTagHelper
    0.60
    XmlEnum
    0.59
    OGND
    0.56
     NSCoder
    0.54
    SourceChecksum
    0.52
    Personendaten
    0.52
     initComponents
    0.51
     Bahkan
    0.50
    Activations Density 0.006%

    No Known Activations