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. 14820
    Prev
    Next
    INDEX
    Explanations

    Java data types and their associated operations within code snippets

    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
     initComponents
    -0.56
    verwijspagina
    -0.52
    msgTypes
    -0.48
    rungsseite
    -0.46
    PageFactory
    -0.45
    IBOutlet
    -0.44
    liceerd
    -0.42
     cref
    -0.42
    èdia
    -0.40
    fjspx
    -0.40
    POSITIVE LOGITS
    VersionUID
    0.83
    getLong
    0.67
    long
    0.65
     BigInt
    0.64
     long
    0.59
    longValue
    0.59
     Long
    0.58
     PyLong
    0.58
    Long
    0.58
    BigInt
    0.56
    Activations Density 0.173%

    No Known Activations