© 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. 19-GEMMASCOPE-RES-16K
    11. 7344
    Prev
    Next
    INDEX
    Explanations

    terms related to experimental study designs and comparisons between control and treatment groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    createClass
    -0.60
     ujednoznacz
    -0.58
    脚注の使い方
    -0.56
    луй
    -0.54
    prefixer
    -0.51
    chiali
    -0.50
    esModule
    -0.50
     AspNetCore
    -0.50
     kasarigan
    -0.50
    WithIOException
    -0.47
    POSITIVE LOGITS
     control
    2.42
     Control
    2.16
    control
    2.10
     controls
    2.06
    Control
    2.01
     CONTROL
    1.93
     Controls
    1.86
    CONTROL
    1.78
    controls
    1.70
     contrôle
    1.63
    Activations Density 1.862%

    No Known Activations