© 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-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 2149
    Prev
    Next
    INDEX
    Explanations

    references to "lines" or "line of thought" in various contexts

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

    Mentions the word "line" or "lines"

    np_acts-logits-general · gemini-2.0-flash

    line or lines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    पूर्ण
    -0.36
     kompakt
    -0.35
     pleinement
    -0.32
     useAppContext
    -0.32
     Paralymp
    -0.31
     accesible
    -0.31
     Sw
    -0.31
     πα
    -0.31
    superuser
    -0.31
     surpresa
    -0.31
    POSITIVE LOGITS
     Line
    1.35
    Line
    1.23
     line
    1.22
     LINE
    1.20
     Lines
    1.11
    LINE
    1.02
    line
    1.01
     LINES
    1.00
    Lines
    0.99
     lines
    0.99
    Activations Density 0.183%

    No Known Activations