© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 12071
    Prev
    Next
    INDEX
    Explanations

    the preposition "in"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .*")]
    -0.52
     AssemblyCompany
    -0.43
    之后的
    -0.39
    MessageTagHelper
    -0.34
    다
    -0.34
     Vorles
    -0.33
    AutoScaleMode
    -0.33
    EndGlobalSection
    -0.33
    HostException
    -0.33
    czego
    -0.32
    POSITIVE LOGITS
     play
    0.75
     sight
    0.70
    play
    0.66
     existence
    0.63
     circulation
    0.62
     place
    0.60
     hand
    0.60
     operation
    0.59
    existence
    0.59
     petto
    0.57
    Activations Density 0.396%

    No Known Activations