© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 16335
    Prev
    Next
    INDEX
    Explanations

    legal terms related to criminal charges and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disambiguazione
    -0.58
     mem
    -0.46
     उन्होंने
    -0.46
    boa
    -0.44
    dr
    -0.44
    mem
    -0.43
    creativecommons
    -0.43
    }}^{\
    -0.42
    fxml
    -0.41
    ci
    -0.41
    POSITIVE LOGITS
    دانشنامهٔ
    0.66
    contentLoaded
    0.66
    ittäin
    0.64
    ustimmung
    0.63
     Diſ
    0.61
    
    0.61
    /**
    0.60
    tvguidetime
    0.60
     Autorisations
    0.60
     bienven
    0.59
    Activations Density 0.848%

    No Known Activations