© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 832
    Prev
    Next
    INDEX
    Explanations

    phrases related to missed opportunities and lack of chances

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

    Negation, often followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    never came

    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
     autorytatywna
    -0.62
     архивлан
    -0.48
     Exactos
    -0.46
     EconPapers
    -0.45
    fjspx
    -0.44
     noDo
    -0.43
    complexContent
    -0.42
     Taktlose
    -0.42
    medriver
    -0.42
    Jeografia
    -0.42
    POSITIVE LOGITS
     sempat
    0.49
    atteindre
    0.46
     Messung
    0.40
     успе
    0.39
     never
    0.39
    ECONDS
    0.38
     fırs
    0.38
     mancha
    0.37
     koke
    0.37
     Flucht
    0.37
    Activations Density 0.514%

    No Known Activations