© 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. 14742
    Prev
    Next
    INDEX
    Explanations

    references to systems, processes, or components related to data or resource management

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

    registration or registering

    np_acts-logits-general · gemini-2.0-flash

    registering or registration

    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
     ब्रेकडाउन
    -0.56
     Ronde
    -0.49
    weih
    -0.47
    Gentile
    -0.47
    runde
    -0.46
    stdc
    -0.45
    (!__
    -0.42
     Citroen
    -0.42
    ukkah
    -0.42
     iload
    -0.41
    POSITIVE LOGITS
     register
    3.80
     registration
    3.79
     registering
    3.54
     Register
    3.48
     Registration
    3.47
     registered
    3.47
     REGISTER
    3.34
     registers
    3.31
    register
    3.30
     registrations
    3.30
    Activations Density 0.235%

    No Known Activations