© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 8825
    Prev
    Next
    INDEX
    Explanations

    contexts involving exposure or vulnerability in front of others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ;|
    -0.60
    .³
    -0.60
     kB
    -0.60
    });*/
    -0.59
    addContainerGap
    -0.59
     ?</
    -0.58
     ‡
    -0.56
    :|
    -0.56
    stylers
    -0.55
    KBS
    -0.54
    POSITIVE LOGITS
     before
    1.25
     Before
    1.18
    before
    1.14
     BEFORE
    1.07
    Before
    1.07
    BEFORE
    1.04
     devant
    0.99
     delante
    0.96
     davanti
    0.92
     front
    0.91
    Activations Density 0.107%

    No Known Activations