© 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. 4546
    Prev
    Next
    INDEX
    Explanations

    phrases related to past managerial roles and relevant evaluations

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

    prior or previous states

    np_acts-logits-general · gemini-2.0-flash

    prior, former, previously

    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
    featureID
    -0.72
     propOrder
    -0.69
     Normdatei
    -0.63
    aarrggbb
    -0.62
    CppCodeGen
    -0.59
    MigrationBuilder
    -0.59
    awtextra
    -0.58
    balleur
    -0.58
    parsedMessage
    -0.57
    AndEndTag
    -0.57
    POSITIVE LOGITS
     previously
    1.13
     Previously
    1.13
     previous
    1.12
    Previously
    1.07
     tidligere
    1.05
    previous
    0.99
     Previous
    0.96
     earlier
    0.96
     formerly
    0.95
    previously
    0.94
    Activations Density 0.456%

    No Known Activations