© 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. 1648
    Prev
    Next
    INDEX
    Explanations

    phrases related to disclaimers and informational purposes

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

    Followed by "only"

    np_acts-logits-general · gemini-2.0-flash

    exclusivity and limitation

    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
    Kjelder
    -0.67
    cydow
    -0.53
    큼
    -0.53
    ReusableCell
    -0.53
    grà
    -0.51
    Бахар
    -0.49
     AssemblyCulture
    -0.48
     itinéraires
    -0.48
    MethodManager
    -0.47
     <>",
    -0.47
    POSITIVE LOGITS
     only
    4.35
    only
    3.64
    Only
    3.37
     Only
    3.25
     ONLY
    2.96
    ONLY
    2.95
     только
    2.73
     seulement
    2.73
     tylko
    2.51
     uniquement
    2.34
    Activations Density 1.983%

    No Known Activations