© 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. 14686
    Prev
    Next
    INDEX
    Explanations

    phrases indicating necessity, conditions, or requirements related to health and legal contexts

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

    Something is needed, required, or warranted

    np_acts-logits-general · gemini-2.0-flash

    is needed or warranted

    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
    RTDA
    -0.64
    Rhestr
    -0.56
    Palmar
    -0.53
    AnimationsModule
    -0.53
     enfrenta
    -0.52
     QtCore
    -0.48
    agisse
    -0.47
     Aner
    -0.47
    mbing
    -0.47
    ControllerTest
    -0.46
    POSITIVE LOGITS
     needed
    0.92
     required
    0.87
    tvguidetime
    0.80
     forthcoming
    0.80
     warranted
    0.79
     desired
    0.77
     necessary
    0.76
     preferred
    0.74
     involved
    0.73
     possible
    0.72
    Activations Density 0.622%

    No Known Activations