Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 5978
    Prev
    Next
    INDEX
    Explanations

    references to page numbers or related identifiers within a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 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
    BagConstraints
    -0.54
    isNotNull
    -0.41
    <bos>
    -0.41
    TestingModule
    -0.40
    Autowired
    -0.39
    SuccessListener
    -0.39
     Trust
    -0.37
     diper
    -0.37
     Drexel
    -0.36
    CppMethod
    -0.35
    POSITIVE LOGITS
     page
    1.40
    Page
    1.38
     Page
    1.37
    page
    1.34
     PAGE
    1.26
     getPage
    1.23
    PAGE
    1.18
    setPage
    1.16
     Pages
    1.14
    getPage
    1.13
    Activations Density 0.083%

    No Known Activations