© 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. 22-GEMMASCOPE-RES-16K
    11. 3622
    Prev
    Next
    INDEX
    Explanations

    asynchronous code patterns and functions

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

    Code snippets and numbers

    np_acts-logits-general · gemini-2.0-flash

    induced active receptor conformation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.59
    enderror
    -0.55
    cupertino
    -0.53
     estekak
    -0.51
     geni
    -0.51
    artes
    -0.49
    addContainerGap
    -0.48
    ">//
    -0.47
    ViewById
    -0.46
     invokingState
    -0.46
    POSITIVE LOGITS
    ScopeManager
    0.65
     policiales
    0.63
    __":
    0.62
     mío
    0.60
     cérami
    0.60
     kveld
    0.59
     esercit
    0.59
     Efq
    0.59
     houſe
    0.59
    rebbero
    0.58
    Activations Density 0.064%

    No Known Activations