© 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. 24-GEMMASCOPE-RES-16K
    11. 174
    Prev
    Next
    INDEX
    Explanations

    terms associated with governance and authority

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

    Prepositions after named entities

    np_acts-logits-general · gemini-2.0-flash

    systems and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.69
     EconPapers
    -0.66
    findpost
    -0.65
    帖最后由
    -0.65
     MainAxisSize
    -0.64
    addPreferredGap
    -0.63
     Italijanski
    -0.63
    principalColumn
    -0.62
    +#+#
    -0.60
    SBATCH
    -0.59
    POSITIVE LOGITS
     geworden
    0.36
    melidir
    0.32
    也是
    0.28
     nonché
    0.28
     därför
    0.27
    単
    0.27
     zweier
    0.26
    ayant
    0.25
     where
    0.25
     prime
    0.25
    Activations Density 0.489%

    No Known Activations