© 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. 6824
    Prev
    Next
    INDEX
    Explanations

    technical terms and identifiers related to programming and data handling

    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
    Rohy
    -0.94
     Мексичка
    -0.94
    RenderAtEndOf
    -0.94
     $_(
    -0.93
     queſta
    -0.92
    AddTagHelper
    -0.88
     zwiſchen
    -0.85
    uxxxx
    -0.83
    iſen
    -0.83
     MainAxisSize
    -0.82
    POSITIVE LOGITS
    .
    0.40
     instead
    0.28
     fjor
    0.25
    expliquer
    0.22
     kveld
    0.21
     conmigo
    0.21
     Instead
    0.21
    (
    0.21
    You
    0.20
    effectuer
    0.20
    Activations Density 0.194%

    No Known Activations