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. 24-GEMMASCOPE-RES-16K
    6. 1070
    Prev
    Next
    INDEX
    Explanations

    technical terms related to computer hardware and issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    system restarting and reinstalling

    np_acts-logits-general · gemini-2.0-flash

    system reboot or reinstallation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    entrySet
    -0.34
    Discount
    -0.34
     gloire
    -0.33
    žiu
    -0.33
    discount
    -0.33
    omány
    -0.32
    +#+
    -0.32
    Steady
    -0.31
     zijne
    -0.31
     Steady
    -0.30
    POSITIVE LOGITS
     resets
    0.69
     reboot
    0.65
     reset
    0.65
     reinstall
    0.65
     wipe
    0.64
     resetting
    0.61
     restores
    0.59
     restart
    0.58
     restore
    0.57
    Jeografia
    0.56
    Activations Density 0.269%

    No Known Activations