© 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. 12-GEMMASCOPE-RES-16K
    6. 6237
    Prev
    Next
    INDEX
    Explanations

    disruptive behaviors or problematic individuals in a workplace context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ंदीखरीदारी
    -0.46
    Manbalar
    -0.45
    يميديا
    -0.44
    lanması
    -0.43
    TagMode
    -0.43
    PyExc
    -0.43
    woff
    -0.41
    slidesPer
    -0.41
     gyhoeddwyd
    -0.41
     üzere
    -0.40
    POSITIVE LOGITS
    SpringRunner
    0.50
     Obrador
    0.47
    localctx
    0.44
    ItemBackground
    0.41
     Cicero
    0.41
    offsetof
    0.41
    bitField
    0.40
    optionalTypeArgs
    0.39
     MonoBehaviour
    0.39
    ANTLR
    0.38
    Activations Density 0.177%

    No Known Activations