© 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. 20-GEMMASCOPE-RES-16K
    6. 3530
    Prev
    Next
    INDEX
    Explanations

    instances of the word "host" and related variations, indicating a focus on hosting-related concepts

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

    references to hosting or hosts in various contexts (events, technical systems, parties, etc.).

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TemporalType
    -0.59
     vVar
    -0.57
    GraphicsUnit
    -0.57
    julie
    -0.55
     jenny
    -0.54
    Notae
    -0.50
    RegistryLite
    -0.49
    Autoritní
    -0.48
     Elmer
    -0.48
    IANGLES
    -0.48
    POSITIVE LOGITS
     Host
    0.86
    Host
    0.84
    host
    0.82
     host
    0.80
    getHost
    0.79
     HOST
    0.77
    HOST
    0.75
    ost
    0.72
     hosting
    0.72
    cast
    0.69
    Activations Density 0.101%

    No Known Activations