© 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. 28-GEMMASCOPE-RES-16K
    6. 8629
    Prev
    Next
    INDEX
    Explanations

    terms related to implications and legal responsibilities

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

    "Imp" followed by words related to implantation or legal terms

    np_acts-logits-general · gemini-2.0-flash

    implanted, imposing, impermissible, implied

    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
    RectangleBorder
    -0.55
    findpost
    -0.48
     CanadaChoose
    -0.47
     lluvia
    -0.46
     soin
    -0.46
     esternos
    -0.44
     gradova
    -0.44
     Exactos
    -0.43
    ukunft
    -0.42
     bera
    -0.42
    POSITIVE LOGITS
     Imp
    0.96
    Imp
    0.80
     imp
    0.73
     Im
    0.72
     IMP
    0.69
     IM
    0.65
    imp
    0.64
     Imper
    0.63
     im
    0.59
     IMPER
    0.59
    Activations Density 0.143%

    No Known Activations