© 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. 14842
    Prev
    Next
    INDEX
    Explanations

    terms related to construction and destruction processes

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

    ending in "ct" or beginning "conne", "sele", "constru"

    np_acts-logits-general · gemini-2.0-flash

    constructive, direction

    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
    •Steering experiments: Gemma 2-2B / 10-GEMMASCOPE-RES-16K

    No Comments

    Negative Logits
    sizeCache
    -0.62
     Mous
    -0.58
     FormData
    -0.58
     تضيفلها
    -0.56
    iddhar
    -0.54
    AddTagHelper
    -0.53
    jasper
    -0.52
     compat
    -0.52
     newArray
    -0.51
     Drip
    -0.51
    POSITIVE LOGITS
    cts
    0.92
    ctor
    0.85
    cti
    0.80
    cted
    0.80
    ctors
    0.79
    actor
    0.75
    cting
    0.74
    ctid
    0.73
    cto
    0.73
    ctions
    0.71
    Activations Density 0.347%

    No Known Activations