© 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-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 7318
    Prev
    Next
    INDEX
    Explanations

    code segments related to file handling and data management

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

    Code related to JIT or file access

    np_acts-logits-general · gemini-2.0-flash

    direct access or dictionary lookup

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
    Numb
    -0.49
    Obj
    -0.49
     obj
    -0.47
     Pic
    -0.47
    Btn
    -0.46
    adress
    -0.46
    Pic
    -0.46
    ',"
    -0.45
     ","
    -0.44
     Cute
    -0.44
    POSITIVE LOGITS
     متعلقه
    0.72
    Personendaten
    0.68
     henvisninger
    0.66
     विश्वसनीयता
    0.62
    fois
    0.61
     avoient
    0.61
    MLLoader
    0.61
     dépens
    0.61
    ModelState
    0.61
     médec
    0.59
    Activations Density 0.589%

    No Known Activations