© 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. 10-GEMMASCOPE-RES-16K
    6. 11046
    Prev
    Next
    INDEX
    Explanations

    references to influencing or impacting others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyTitle
    -0.61
     fhort
    -0.60
     Houſe
    -0.54
     fevere
    -0.52
     GenerationType
    -0.52
     idolat
    -0.52
    »։
    -0.52
     Encyclo
    -0.50
    MessageTagHelper
    -0.50
     
    -0.50
    POSITIVE LOGITS
     others
    1.24
    others
    1.20
     Others
    1.20
    Others
    1.19
     OTHERS
    1.07
    OTHERS
    0.81
     دیگران
    0.75
    別人
    0.66
    别人
    0.66
    其他人
    0.59
    Activations Density 0.164%

    No Known Activations