© 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. 14-GEMMASCOPE-RES-16K
    11. 6837
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to phonology and memory structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chaik
    -0.50
     adjourned
    -0.49
     purpoſe
    -0.47
    premi
    -0.47
     logistical
    -0.46
    ConstraintMaker
    -0.45
     adjourn
    -0.45
     trib
    -0.45
     administr
    -0.44
     civi
    -0.44
    POSITIVE LOGITS
    fjspx
    0.44
     يتيمه
    0.43
     transparentes
    0.42
     capucha
    0.41
     costumbre
    0.40
     pinulongan
    0.40
     humedad
    0.40
    ContentAsync
    0.39
     habituales
    0.39
     nemlig
    0.39
    Activations Density 0.214%

    No Known Activations