© 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. 40-GEMMASCOPE-RES-16K
    6. 5182
    Prev
    Next
    INDEX
    Explanations

    elements related to crime and legal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EndContext
    -0.46
    modelBuilder
    -0.44
     Signalez
    -0.43
    ellees
    -0.43
    quelize
    -0.41
    vician
    -0.40
    matchCondition
    -0.38
    ictwa
    -0.36
    FormTagHelper
    -0.35
    igurumi
    -0.35
    POSITIVE LOGITS
     media
    2.03
     headlines
    1.65
    media
    1.58
     mídia
    1.54
     newspapers
    1.54
     press
    1.49
     news
    1.47
     médias
    1.46
     prensa
    1.45
    媒体
    1.41
    Activations Density 0.804%

    No Known Activations