© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 15879
    Prev
    Next
    INDEX
    Explanations

    terms related to legal and administrative processes

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

    before domain

    np_acts-logits-general · gemini-2.0-flash

    represent domain building ensure with

    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
    …………………………………………
    -1.23
     themſelves
    -1.21
    ————————————————
    -1.17
     Shakspeare
    -1.16
    ghijklmnop
    -1.15
     Monfieur
    -1.07
     Constantinople
    -1.03
     pleaſure
    -1.02
     MERCHANTABILITY
    -1.02
     commonwealth
    -1.01
    POSITIVE LOGITS
     liée
    0.58
     fijar
    0.52
    nonatomic
    0.50
    ↵
    0.50
     liées
    0.50
     fapt
    0.50
     Juifs
    0.48
    0.47
     jiwa
    0.47
    resave
    0.47
    Activations Density 0.642%
    No Known Activations