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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 12836
    Prev
    Next
    INDEX
    Explanations

    Java import statements for libraries and classes

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

    "import" statements followed by "org" or "("

    np_acts-logits-general · gemini-2.0-flash

    org

    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
    InjectAttribute
    -0.57
     aDecoder
    -0.52
    menopausal
    -0.47
    requireNonNull
    -0.45
    ContentAsync
    -0.45
    ViewFeatures
    -0.45
    ंदीखरीदारी
    -0.45
     Kabir
    -0.44
     deltaTime
    -0.43
     chi̍t
    -0.42
    POSITIVE LOGITS
     org
    2.58
     organization
    2.56
    org
    2.40
     Organization
    2.37
    Org
    2.33
     Org
    2.31
     organisation
    2.29
    Organization
    2.23
    organization
    2.20
     Organisation
    2.16
    Activations Density 0.132%

    No Known Activations