© 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. 1-GEMMASCOPE-RES-16K
    6. 3411
    Prev
    Next
    INDEX
    Explanations

    terms related to seizure of property or evidence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MENAFN
    -0.48
    jména
    -0.47
     Brito
    -0.47
    principalColumn
    -0.44
    følge
    -0.44
     disposiciones
    -0.44
    scalatest
    -0.42
    FetchType
    -0.42
    drawiam
    -0.41
    lujah
    -0.41
    POSITIVE LOGITS
     conv
    0.66
     Seiz
    0.54
     ri
    0.54
     seizure
    0.54
    precision
    0.54
    tagHelperRunner
    0.53
     seized
    0.53
     courtesy
    0.52
     inc
    0.51
    conv
    0.51
    Activations Density 0.481%

    No Known Activations