© 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. 30-GEMMASCOPE-RES-16K
    11. 7940
    Prev
    Next
    INDEX
    Explanations

    key figures and pivotal decisions in historical contexts

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

    suggesting taking advantage or exploiting

    np_acts-logits-general · gemini-2.0-flash

    take advantage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AnchorStyles
    -0.48
    endphp
    -0.43
    cinfo
    -0.42
    ronpa
    -0.42
    
    -0.41
     Habit
    -0.40
     readability
    -0.39
     Proto
    -0.39
    antası
    -0.38
    AssignableFrom
    -0.38
    POSITIVE LOGITS
     aprovecha
    1.59
     aprovechar
    1.52
     aprove
    1.45
     exploiting
    1.44
     utilize
    1.39
     wykorzyst
    1.38
     memanfaatkan
    1.38
     exploited
    1.38
     exploit
    1.38
    利用
    1.36
    Activations Density 0.681%

    No Known Activations