© 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-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 10744
    Prev
    Next
    INDEX
    Explanations

    nouns related to perceptions and impressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "impression" or variants

    np_acts-logits-general · gemini-2.0-flash

    impression or impress

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    httphttps
    -0.52
     NavController
    -0.51
    KommentareTeilen
    -0.47
    AxisAlignment
    -0.39
    Portale
    -0.39
     propOrder
    -0.38
     Taktlose
    -0.38
     calendriers
    -0.36
    DotNetBar
    -0.35
    UIControlState
    -0.35
    POSITIVE LOGITS
     impression
    2.70
     impressions
    2.47
    impression
    2.36
     Impression
    2.19
    Impression
    2.08
     Impressions
    2.00
     impress
    2.00
     impresion
    1.98
     impressed
    1.97
    impres
    1.96
    Activations Density 0.245%

    No Known Activations