© 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-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 13458
    Prev
    Next
    INDEX
    Explanations

    references to group affiliation and membership

    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
    Nuorodos
    -0.81
     defaultstate
    -0.76
     Pasteur
    -0.74
     EIS
    -0.74
    WithIOException
    -0.73
     Eri
    -0.72
    ')")
    -0.72
     RTS
    -0.71
     '':
    -0.70
     GenerationType
    -0.70
    POSITIVE LOGITS
     members
    3.31
    members
    2.93
     member
    2.93
     Members
    2.84
    Members
    2.80
     MEMBERS
    2.62
    member
    2.53
     membres
    2.41
     Member
    2.39
     MEMBER
    2.29
    Activations Density 0.046%

    No Known Activations