© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 7800
    Prev
    Next
    INDEX
    Explanations

    phrases that initiate statements of existence or presence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 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
    Personendaten
    -0.69
    
    -0.68
     المعيارى
    -0.66
     صوتيه
    -0.62
     ProtoMessage
    -0.60
     PeEnEo
    -0.59
     Roskov
    -0.56
     disambiguazione
    -0.55
     Италијани
    -0.55
    webElementXpaths
    -0.53
    POSITIVE LOGITS
     There
    1.53
    There
    1.23
     THERE
    0.76
    They
    0.76
     They
    0.75
    THERE
    0.71
     Theres
    0.69
     Here
    0.68
     It
    0.66
     These
    0.65
    Activations Density 0.026%

    No Known Activations