© 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-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 1663
    Prev
    Next
    INDEX
    Explanations

    terms related to impressions and receptions

    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
    &=&
    -0.76
    smh
    -0.71
    tute
    -0.70
    ²)
    -0.67
    ‚¬
    -0.67
    +:+
    -0.67
     publiques
    -0.66
    ("")]
    -0.65
     apporter
    -0.65
     Carney
    -0.65
    POSITIVE LOGITS
     impression
    1.51
     Impression
    1.23
    impression
    1.21
    Impression
    1.19
     impressions
    1.19
    impres
    1.11
     Impressions
    1.04
     reception
    1.03
     Reception
    0.98
     lobby
    0.97
    Activations Density 0.074%

    No Known Activations