© 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. 14-GEMMASCOPE-RES-16K
    11. 8202
    Prev
    Next
    INDEX
    Explanations

    references to handles and rods related to various tools and devices

    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
     Infórmanos
    -0.46
    裟
    -0.44
     désolés
    -0.39
    BeginInit
    -0.39
    '][$
    -0.39
    othelioma
    -0.38
     acreage
    -0.38
    scriptcase
    -0.38
    Rptr
    -0.38
    ₪
    -0.38
    POSITIVE LOGITS
     stick
    0.69
    eseorang
    0.68
     shaft
    0.68
     rods
    0.65
     tube
    0.63
     needle
    0.61
     rod
    0.60
     Stick
    0.58
    stick
    0.58
    Stick
    0.56
    Activations Density 0.374%

    No Known Activations