© 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. 24-GEMMASCOPE-RES-16K
    11. 3215
    Prev
    Next
    INDEX
    Explanations

    concepts related to emotional resilience and supportive human interactions

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

    before coordinating conjunctions

    np_acts-logits-general · gemini-2.0-flash

    conjunctions or contrasting clauses

    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
    parsedMessage
    -0.59
     EconPapers
    -0.59
    Бахар
    -0.59
     disambiguazione
    -0.56
     myſelf
    -0.55
     imagui
    -0.55
    EDEFAULT
    -0.54
    featureID
    -0.53
     meriva
    -0.53
     laſſen
    -0.52
    POSITIVE LOGITS
     but
    1.13
     nhưng
    0.93
     namun
    0.90
     pero
    0.88
    but
    0.87
     tetapi
    0.81
     mutta
    0.80
     yet
    0.77
    แต่
    0.75
     tapi
    0.73
    Activations Density 0.470%

    No Known Activations