© 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. 2659
    Prev
    Next
    INDEX
    Explanations

    references to specific entities or variables labeled as "P" followed by numbers

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

    Followed by two capital letters

    np_acts-logits-general · gemini-2.0-flash

    P-starts

    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
     كومونز
    -0.69
    Personendaten
    -0.65
    WithIOException
    -0.64
    (!__
    -0.60
    뷔
    -0.58
    addContainerGap
    -0.52
    principalColumn
    -0.51
    RTLU
    -0.51
    matchCondition
    -0.50
    ViewImports
    -0.50
    POSITIVE LOGITS
     Legendre
    0.46
    Spice
    0.43
     SwiftUI
    0.43
     Pirates
    0.41
    createCanvas
    0.41
     Curie
    0.41
     counselor
    0.40
    ])).
    0.40
     iniquity
    0.40
    Życiorys
    0.40
    Activations Density 0.171%

    No Known Activations