Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 9279
    Prev
    Next
    INDEX
    Explanations

    references to high-risk investments or speculative ventures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     street
    -0.45
     privacy
    -0.42
    Blur
    -0.37
     volunteer
    -0.37
     screen
    -0.37
     Ulm
    -0.37
     living
    -0.36
     joy
    -0.36
     cuc
    -0.36
    noStroke
    -0.36
    POSITIVE LOGITS
     estekak
    0.78
    脚注の使い方
    0.67
     mines
    0.65
     mining
    0.63
     pinulongan
    0.62
    RectangleBorder
    0.59
     miners
    0.58
     geologists
    0.58
     exploration
    0.58
     oil
    0.58
    Activations Density 0.215%

    No Known Activations