© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 2978
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of providing essential services and features

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

    "Everything [someone] needs"

    np_acts-logits-general · gemini-2.0-flash

    everything needed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ebaran
    -0.40
    terus
    -0.39
     zobac
    -0.39
    ificantly
    -0.39
    micha
    -0.38
     afhankelijk
    -0.38
    andidates
    -0.38
    INDICATOR
    -0.37
    modelBuilder
    -0.37
     élevée
    -0.37
    POSITIVE LOGITS
     amenities
    0.78
     equipped
    0.69
     comforts
    0.63
    equipped
    0.62
     Equipped
    0.60
     equip
    0.60
     equipping
    0.59
    Amenities
    0.57
     equipment
    0.57
    Equip
    0.55
    Activations Density 0.192%

    No Known Activations