© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 93367
    Prev
    Next
    INDEX
    Explanations

    concepts related to prevention and protection in various contexts

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

    law and order actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GenerationType
    -0.71
    Földrajzportál
    -0.68
    MessageTagHelper
    -0.67
     ſeyn
    -0.65
     $_-
    -0.65
    <unused3>
    -0.65
    <pad>
    -0.65
    <unused28>
    -0.64
    <unused17>
    -0.64
    <unused8>
    -0.64
    POSITIVE LOGITS
    Források
    0.28
     باخ
    0.26
     active
    0.25
     
    0.24
    reactstrap
    0.24
    wyczaj
    0.23
    UIControlState
    0.22
    Quel
    0.22
     calme
    0.22
     always
    0.22
    Activations Density 0.040%

    No Known Activations