© 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. 9327
    Prev
    Next
    INDEX
    Explanations

    terms related to biological processes and medical conditions

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

    Followed by "other"

    np_acts-logits-general · gemini-2.0-flash

    other than

    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
    #+#
    -0.75
     AssemblyCompany
    -0.62
    IUrlHelper
    -0.60
    enderror
    -0.59
    "}")
    -0.58
    gameserver
    -0.56
     NgModule
    -0.56
    TagHelper
    -0.56
    ')));
    -0.55
    Personensuche
    -0.54
    POSITIVE LOGITS
     other
    2.47
     besides
    2.37
    besides
    2.17
    other
    2.17
     aside
    1.94
     beyond
    1.93
     selain
    1.85
    Other
    1.82
    beyond
    1.82
     apart
    1.81
    Activations Density 1.078%

    No Known Activations