© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 27-GEMMASCOPE-RES-16K
    11. 8336
    Prev
    Next
    INDEX
    Explanations

    instances of the word "host" and its variations related to events and media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MessageOf
    -0.46
    //
    -0.40
    Kaynakça
    -0.40
    Jeografia
    -0.37
    UniformLocation
    -0.36
     sessionFactory
    -0.35
    Související
    -0.34
     cref
    -0.33
     Lillie
    -0.33
     Preferencias
    -0.33
    POSITIVE LOGITS
     Host
    1.13
     host
    1.12
     HOST
    1.09
    getHost
    1.09
    Host
    1.09
    host
    1.02
     Hosts
    0.94
     hosts
    0.94
     hosted
    0.93
     hosting
    0.92
    Activations Density 0.096%

    No Known Activations