© 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. 41-GEMMASCOPE-RES-16K
    11. 9266
    Prev
    Next
    INDEX
    Explanations

    words related to negative or undesirable circumstances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Plenum
    -0.46
     stro
    -0.42
     ब्रेकडाउन
    -0.40
     Incorrect
    -0.40
    bbero
    -0.39
    ValueGenerated
    -0.39
     weakly
    -0.39
     Detail
    -0.39
    WithIOException
    -0.39
    glLoad
    -0.38
    POSITIVE LOGITS
    necessary
    0.56
    necessarily
    0.54
    fortunate
    0.54
    relenting
    0.54
    usually
    0.52
    official
    0.52
    ruly
    0.52
    precedented
    0.52
    packing
    0.52
    wanted
    0.51
    Activations Density 0.134%

    No Known Activations