© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 15803
    Prev
    Next
    INDEX
    Explanations

    references to electronic devices and their functionalities

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

    Portability or compact design

    np_acts-logits-general · gemini-2.0-flash

    portable, carrying, or traveling

    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
     ویکی‌پدیای
    -0.66
     >=",
    -0.64
    laut
    -0.63
    AnimationsModule
    -0.61
    dicionado
    -0.61
    fjspx
    -0.56
    EndTag
    -0.54
     iprot
    -0.53
     Inquirer
    -0.52
     عليكم
    -0.51
    POSITIVE LOGITS
     portability
    1.37
     portable
    1.24
     carry
    1.23
     carried
    1.17
     carrying
    1.16
     traveling
    1.14
     Carry
    1.13
    Carry
    1.10
    carry
    1.10
     travelling
    1.10
    Activations Density 0.242%

    No Known Activations