© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 5127
    Prev
    Next
    INDEX
    Explanations

    sentences containing personal reflections and emotions

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

    followed by forms of "be" or "'s"

    np_acts-logits-general · gemini-2.0-flash

    past states or prior usage

    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
     employing
    -0.60
     uParam
    -0.58
    ORAGE
    -0.57
    SourceChecksum
    -0.56
     >=",
    -0.54
    TagMode
    -0.53
    \{\\
    -0.52
     Chwiliwch
    -0.51
     ensuing
    -0.50
    setVerticalGroup
    -0.50
    POSITIVE LOGITS
     used
    2.88
    used
    2.62
     Used
    2.60
    Used
    2.59
     USED
    2.40
    USED
    1.88
     usado
    1.74
     usada
    1.58
     usados
    1.56
     uſed
    1.55
    Activations Density 0.246%

    No Known Activations