© 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 EvalsExportsAPI 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. 13741
    Prev
    Next
    INDEX
    Explanations

    key moments in personal narratives that signify significant turning points or transformations

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

    "Turning point" or decisive moment

    np_acts-logits-general · gemini-2.0-flash

    turning point

    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
    üyor
    -0.36
     Tujuan
    -0.34
    PCM
    -0.32
     nød
    -0.32
    Rujuakan
    -0.32
     deber
    -0.31
     feroit
    -0.31
     préfé
    -0.31
     plads
    -0.31
    WriteLiteral
    -0.31
    POSITIVE LOGITS
     tipping
    1.16
     turning
    1.15
     pivotal
    1.13
     decisive
    1.06
     breakthrough
    0.98
     catalyst
    0.97
    turning
    0.95
     deciding
    0.88
     moment
    0.87
     Turning
    0.85
    Activations Density 0.328%

    No Known Activations