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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 10346
    Prev
    Next
    INDEX
    Explanations

    phrases suggesting skepticism or caution in discussions

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

    words describing negative or problematic characteristics and situations.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.73
    MigrationBuilder
    -0.62
     itſelf
    -0.59
     myſelf
    -0.57
     $_"
    -0.56
    uxxxx
    -0.54
    IGraphics
    -0.54
    #+#
    -0.51
    -------------</
    -0.51
     Efq
    -0.50
    POSITIVE LOGITS
     […]
    1.20
    ↵
    1.06
    ↵↵
    1.03
    -\\
    1.00
    <eos>
    0.94
    ,...
    0.90
    ...
    0.88
     [...]
    0.87
     =
    0.84
    -...
    0.84
    Activations Density 20.363%

    No Known Activations