© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 4536
    Prev
    Next
    INDEX
    Explanations

    educational qualifications and professional achievements

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

    Comes before fields of study or school names

    np_acts-logits-general · gemini-2.0-flash

    academic completion and attendance

    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
    ſelves
    -0.94
     ſche
    -0.93
     مشين
    -0.91
     esternos
    -0.90
     Anſ
    -0.89
    <unused43>
    -0.88
    <unused79>
    -0.88
     Majefty
    -0.88
    <unused41>
    -0.88
    <unused28>
    -0.87
    POSITIVE LOGITS
     completed
    0.38
     studied
    0.35
     graduated
    0.32
    <eos>
    0.27
     followed
    0.26
     the
    0.26
     completion
    0.25
     finished
    0.25
     Flasche
    0.23
     completing
    0.23
    Activations Density 0.088%

    No Known Activations