© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 11537
    Prev
    Next
    INDEX
    Explanations

    phrases that introduce additional information or elaboration

    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
     zwiſchen
    -0.81
     deſſen
    -0.78
    bildtitel
    -0.77
    <unused20>
    -0.77
    ſicht
    -0.77
    <unused51>
    -0.77
     queſto
    -0.77
    <unused74>
    -0.77
    <unused41>
    -0.77
    <unused43>
    -0.77
    POSITIVE LOGITS
     late
    0.29
     informée
    0.29
    NullException
    0.28
     associated
    0.27
     sp
    0.26
     engaging
    0.26
    acyjnych
    0.25
    ,
    0.25
     Censo
    0.25
     while
    0.25
    Activations Density 0.320%

    No Known Activations