© 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-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 1242
    Prev
    Next
    INDEX
    Explanations

    references to police actions and incidents involving law enforcement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atomy
    -0.64
    OrBuilder
    -0.60
    はじめに
    -0.59
    setVerticalGroup
    -0.58
     newOwner
    -0.58
    IBOutlet
    -0.58
     المعيارى
    -0.58
    ocere
    -0.56
    GOTREF
    -0.56
    pushFollow
    -0.56
    POSITIVE LOGITS
     patrolling
    0.98
     dispatched
    0.84
     cordon
    0.83
     deployed
    0.83
     patrols
    0.82
     stationed
    0.76
     investigating
    0.72
     patrol
    0.68
     escort
    0.64
     investigate
    0.64
    Activations Density 0.246%

    No Known Activations