© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12881
    Prev
    Next
    INDEX
    Explanations

    discussions around advice and recommendations

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

    suggestions and directives

    np_acts-logits-general · gemini-2.0-flash

    advice and recommendations

    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
    offsetof
    -0.36
    RegressionTest
    -0.34
     acquaintance
    -0.31
     carried
    -0.30
     демон
    -0.30
     constat
    -0.30
    Característica
    -0.29
    Фак
    -0.29
    Fact
    -0.28
     факт
    -0.28
    POSITIVE LOGITS
     advice
    1.22
     instructions
    1.21
    advice
    1.12
     recommendations
    1.11
     recommended
    1.09
     recommendation
    1.09
    instructions
    1.07
     Advice
    1.06
     instructed
    1.05
     instructs
    1.05
    Activations Density 0.598%

    No Known Activations