© 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. 28-GEMMASCOPE-RES-16K
    11. 7944
    Prev
    Next
    INDEX
    Explanations

    concepts related to societal collapse and transformation

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

    Follows "is" or describes a negative situation

    np_acts-logits-general · gemini-2.0-flash

    world and life in negative states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    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
    -0.54
     kaarangay
    -0.52
    CPtr
    -0.52
    verwijspagina
    -0.52
     للاسماء
    -0.50
    RegistryLite
    -0.50
    TagNumber
    -0.49
    transQ
    -0.47
     wireType
    -0.47
    SizeMode
    -0.46
    POSITIVE LOGITS
     entera
    0.52
     entière
    0.44
     inteiro
    0.44
    BASEPATH
    0.42
    UrlResolution
    0.40
     bgcolor
    0.40
    整体
    0.40
    AutoScale
    0.40
     divided
    0.39
    分成
    0.39
    Activations Density 0.308%

    No Known Activations